diff --git a/docs/_posts/ahmedlone127/2023-09-15-100_sdb_tbb_en.md b/docs/_posts/ahmedlone127/2023-09-15-100_sdb_tbb_en.md new file mode 100644 index 00000000000000..eea668d4b339e8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-100_sdb_tbb_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English 100_sdb_tbb DistilBertEmbeddings from sripadhstudy +author: John Snow Labs +name: 100_sdb_tbb +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`100_sdb_tbb` is a English model originally trained by sripadhstudy. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/100_sdb_tbb_en_5.1.2_3.0_1694784123220.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/100_sdb_tbb_en_5.1.2_3.0_1694784123220.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("100_sdb_tbb","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("100_sdb_tbb", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|100_sdb_tbb| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.0 MB| + +## References + +https://huggingface.co/sripadhstudy/100_SDB_TBB \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version1_en.md b/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version1_en.md new file mode 100644 index 00000000000000..fea219717006e5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English 20split_dataset_version1 DistilBertEmbeddings from Billwzl +author: John Snow Labs +name: 20split_dataset_version1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`20split_dataset_version1` is a English model originally trained by Billwzl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/20split_dataset_version1_en_5.1.2_3.0_1694780611703.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/20split_dataset_version1_en_5.1.2_3.0_1694780611703.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("20split_dataset_version1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("20split_dataset_version1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|20split_dataset_version1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/Billwzl/20split_dataset_version1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version2_en.md b/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version2_en.md new file mode 100644 index 00000000000000..5a5ae58f9c6d35 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version2_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English 20split_dataset_version2 DistilBertEmbeddings from Billwzl +author: John Snow Labs +name: 20split_dataset_version2 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`20split_dataset_version2` is a English model originally trained by Billwzl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/20split_dataset_version2_en_5.1.2_3.0_1694781304116.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/20split_dataset_version2_en_5.1.2_3.0_1694781304116.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("20split_dataset_version2","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("20split_dataset_version2", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|20split_dataset_version2| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.0 MB| + +## References + +https://huggingface.co/Billwzl/20split_dataset_version2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version3_en.md b/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version3_en.md new file mode 100644 index 00000000000000..1676b2b1aa852d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version3_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English 20split_dataset_version3 DistilBertEmbeddings from Billwzl +author: John Snow Labs +name: 20split_dataset_version3 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`20split_dataset_version3` is a English model originally trained by Billwzl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/20split_dataset_version3_en_5.1.2_3.0_1694781556318.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/20split_dataset_version3_en_5.1.2_3.0_1694781556318.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("20split_dataset_version3","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("20split_dataset_version3", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|20split_dataset_version3| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Billwzl/20split_dataset_version3 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version4_en.md b/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version4_en.md new file mode 100644 index 00000000000000..4114cdc080b445 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-20split_dataset_version4_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English 20split_dataset_version4 DistilBertEmbeddings from Billwzl +author: John Snow Labs +name: 20split_dataset_version4 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`20split_dataset_version4` is a English model originally trained by Billwzl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/20split_dataset_version4_en_5.1.2_3.0_1694782055167.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/20split_dataset_version4_en_5.1.2_3.0_1694782055167.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("20split_dataset_version4","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("20split_dataset_version4", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|20split_dataset_version4| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Billwzl/20split_dataset_version4 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-500_sdb_tbb_en.md b/docs/_posts/ahmedlone127/2023-09-15-500_sdb_tbb_en.md new file mode 100644 index 00000000000000..43e9f72176801e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-500_sdb_tbb_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English 500_sdb_tbb DistilBertEmbeddings from sripadhstudy +author: John Snow Labs +name: 500_sdb_tbb +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`500_sdb_tbb` is a English model originally trained by sripadhstudy. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/500_sdb_tbb_en_5.1.2_3.0_1694784390417.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/500_sdb_tbb_en_5.1.2_3.0_1694784390417.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("500_sdb_tbb","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("500_sdb_tbb", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|500_sdb_tbb| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/sripadhstudy/500_SDB_TBB \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-aave_distil_bert_en.md b/docs/_posts/ahmedlone127/2023-09-15-aave_distil_bert_en.md new file mode 100644 index 00000000000000..0c6b3141a32a29 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-aave_distil_bert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English aave_distil_bert DistilBertEmbeddings from csalaam +author: John Snow Labs +name: aave_distil_bert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`aave_distil_bert` is a English model originally trained by csalaam. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/aave_distil_bert_en_5.1.2_3.0_1694781245405.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/aave_distil_bert_en_5.1.2_3.0_1694781245405.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("aave_distil_bert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("aave_distil_bert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|aave_distil_bert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.5 MB| + +## References + +https://huggingface.co/csalaam/AAVE-distil-bert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-absa_with_maskedlm_finetuned_sentihood_en.md b/docs/_posts/ahmedlone127/2023-09-15-absa_with_maskedlm_finetuned_sentihood_en.md new file mode 100644 index 00000000000000..94283894826b54 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-absa_with_maskedlm_finetuned_sentihood_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English absa_with_maskedlm_finetuned_sentihood DistilBertEmbeddings from UchihaMadara +author: John Snow Labs +name: absa_with_maskedlm_finetuned_sentihood +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`absa_with_maskedlm_finetuned_sentihood` is a English model originally trained by UchihaMadara. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/absa_with_maskedlm_finetuned_sentihood_en_5.1.2_3.0_1694786043453.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/absa_with_maskedlm_finetuned_sentihood_en_5.1.2_3.0_1694786043453.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("absa_with_maskedlm_finetuned_sentihood","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("absa_with_maskedlm_finetuned_sentihood", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|absa_with_maskedlm_finetuned_sentihood| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/UchihaMadara/ABSA-with-MaskedLM-finetuned-sentihood \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-ad_distilbert_base_uncased_finetuned_dantest2_en.md b/docs/_posts/ahmedlone127/2023-09-15-ad_distilbert_base_uncased_finetuned_dantest2_en.md new file mode 100644 index 00000000000000..2ac718547ae413 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-ad_distilbert_base_uncased_finetuned_dantest2_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English ad_distilbert_base_uncased_finetuned_dantest2 DistilBertEmbeddings from refringence +author: John Snow Labs +name: ad_distilbert_base_uncased_finetuned_dantest2 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`ad_distilbert_base_uncased_finetuned_dantest2` is a English model originally trained by refringence. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/ad_distilbert_base_uncased_finetuned_dantest2_en_5.1.2_3.0_1694777623781.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/ad_distilbert_base_uncased_finetuned_dantest2_en_5.1.2_3.0_1694777623781.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("ad_distilbert_base_uncased_finetuned_dantest2","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("ad_distilbert_base_uncased_finetuned_dantest2", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|ad_distilbert_base_uncased_finetuned_dantest2| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/refringence/ad-distilbert-base-uncased-finetuned-dantest2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bert_base_uncased_finetuned_imdb_accelerate_en.md b/docs/_posts/ahmedlone127/2023-09-15-bert_base_uncased_finetuned_imdb_accelerate_en.md new file mode 100644 index 00000000000000..8b2b3e14125407 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bert_base_uncased_finetuned_imdb_accelerate_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_imdb_accelerate DistilBertEmbeddings from Arthuerwang +author: John Snow Labs +name: bert_base_uncased_finetuned_imdb_accelerate +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_imdb_accelerate` is a English model originally trained by Arthuerwang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_imdb_accelerate_en_5.1.2_3.0_1694783561288.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_imdb_accelerate_en_5.1.2_3.0_1694783561288.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bert_base_uncased_finetuned_imdb_accelerate","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bert_base_uncased_finetuned_imdb_accelerate", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_imdb_accelerate| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Arthuerwang/bert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bert_distil_ct_en.md b/docs/_posts/ahmedlone127/2023-09-15-bert_distil_ct_en.md new file mode 100644 index 00000000000000..59445a5eb45611 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bert_distil_ct_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bert_distil_ct DistilBertEmbeddings from Contrastive-Tension +author: John Snow Labs +name: bert_distil_ct +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_distil_ct` is a English model originally trained by Contrastive-Tension. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_distil_ct_en_5.1.2_3.0_1694770957596.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_distil_ct_en_5.1.2_3.0_1694770957596.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bert_distil_ct","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bert_distil_ct", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_distil_ct| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Contrastive-Tension/BERT-Distil-CT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bert_distil_nli_ct_en.md b/docs/_posts/ahmedlone127/2023-09-15-bert_distil_nli_ct_en.md new file mode 100644 index 00000000000000..263aedc5f9ebe9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bert_distil_nli_ct_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bert_distil_nli_ct DistilBertEmbeddings from Contrastive-Tension +author: John Snow Labs +name: bert_distil_nli_ct +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_distil_nli_ct` is a English model originally trained by Contrastive-Tension. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_distil_nli_ct_en_5.1.2_3.0_1694771080239.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_distil_nli_ct_en_5.1.2_3.0_1694771080239.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bert_distil_nli_ct","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bert_distil_nli_ct", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_distil_nli_ct| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Contrastive-Tension/BERT-Distil-NLI-CT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bert_name_en.md b/docs/_posts/ahmedlone127/2023-09-15-bert_name_en.md new file mode 100644 index 00000000000000..adb4957f0414db --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bert_name_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bert_name DistilBertEmbeddings from Ondiet +author: John Snow Labs +name: bert_name +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_name` is a English model originally trained by Ondiet. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_name_en_5.1.2_3.0_1694788522767.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_name_en_5.1.2_3.0_1694788522767.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bert_name","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bert_name", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_name| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Ondiet/bert_name \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bert_news_en.md b/docs/_posts/ahmedlone127/2023-09-15-bert_news_en.md new file mode 100644 index 00000000000000..b8f3700c4de564 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bert_news_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bert_news DistilBertEmbeddings from harvinder676 +author: John Snow Labs +name: bert_news +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_news` is a English model originally trained by harvinder676. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_news_en_5.1.2_3.0_1694782914172.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_news_en_5.1.2_3.0_1694782914172.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bert_news","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bert_news", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_news| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/harvinder676/bert-news \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bert_pretrain_en.md b/docs/_posts/ahmedlone127/2023-09-15-bert_pretrain_en.md new file mode 100644 index 00000000000000..34886cf1e9c64d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bert_pretrain_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bert_pretrain DistilBertEmbeddings from catofnull +author: John Snow Labs +name: bert_pretrain +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_pretrain` is a English model originally trained by catofnull. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_pretrain_en_5.1.2_3.0_1694775655895.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_pretrain_en_5.1.2_3.0_1694775655895.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bert_pretrain","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bert_pretrain", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_pretrain| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/catofnull/BERT-Pretrain \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bert_tuned_trial_20_12_2022_en.md b/docs/_posts/ahmedlone127/2023-09-15-bert_tuned_trial_20_12_2022_en.md new file mode 100644 index 00000000000000..dc68fbe89125c0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bert_tuned_trial_20_12_2022_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bert_tuned_trial_20_12_2022 DistilBertEmbeddings from EslamAhmed +author: John Snow Labs +name: bert_tuned_trial_20_12_2022 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_tuned_trial_20_12_2022` is a English model originally trained by EslamAhmed. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_tuned_trial_20_12_2022_en_5.1.2_3.0_1694784215749.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_tuned_trial_20_12_2022_en_5.1.2_3.0_1694784215749.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bert_tuned_trial_20_12_2022","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bert_tuned_trial_20_12_2022", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_tuned_trial_20_12_2022| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|447.5 MB| + +## References + +https://huggingface.co/EslamAhmed/BERT_tuned_trial_20-12-2022 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bertfined_finetunedmodel_fakenews_en.md b/docs/_posts/ahmedlone127/2023-09-15-bertfined_finetunedmodel_fakenews_en.md new file mode 100644 index 00000000000000..e11b830920c741 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bertfined_finetunedmodel_fakenews_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bertfined_finetunedmodel_fakenews DistilBertEmbeddings from Sakil +author: John Snow Labs +name: bertfined_finetunedmodel_fakenews +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bertfined_finetunedmodel_fakenews` is a English model originally trained by Sakil. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bertfined_finetunedmodel_fakenews_en_5.1.2_3.0_1694790199446.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bertfined_finetunedmodel_fakenews_en_5.1.2_3.0_1694790199446.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bertfined_finetunedmodel_fakenews","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bertfined_finetunedmodel_fakenews", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bertfined_finetunedmodel_fakenews| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|402.3 MB| + +## References + +https://huggingface.co/Sakil/bertfined_finetunedmodel_fakenews \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bertino_it.md b/docs/_posts/ahmedlone127/2023-09-15-bertino_it.md new file mode 100644 index 00000000000000..154883d0285a3d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bertino_it.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Italian bertino DistilBertEmbeddings from indigo-ai +author: John Snow Labs +name: bertino +date: 2023-09-15 +tags: [distilbert, it, open_source, fill_mask, onnx] +task: Embeddings +language: it +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bertino` is a Italian model originally trained by indigo-ai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bertino_it_5.1.2_3.0_1694780792709.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bertino_it_5.1.2_3.0_1694780792709.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bertino","it") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bertino", "it") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bertino| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|it| +|Size:|253.0 MB| + +## References + +https://huggingface.co/indigo-ai/BERTino \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-bertino_lsg_en.md b/docs/_posts/ahmedlone127/2023-09-15-bertino_lsg_en.md new file mode 100644 index 00000000000000..30ab6840313ef8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-bertino_lsg_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English bertino_lsg DistilBertEmbeddings from efederici +author: John Snow Labs +name: bertino_lsg +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bertino_lsg` is a English model originally trained by efederici. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bertino_lsg_en_5.1.2_3.0_1694772729108.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bertino_lsg_en_5.1.2_3.0_1694772729108.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("bertino_lsg","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("bertino_lsg", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bertino_lsg| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|263.3 MB| + +## References + +https://huggingface.co/efederici/bertino-lsg \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-burmese_finetuned_distilbert_portuguese_en.md b/docs/_posts/ahmedlone127/2023-09-15-burmese_finetuned_distilbert_portuguese_en.md new file mode 100644 index 00000000000000..2f8110527e6642 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-burmese_finetuned_distilbert_portuguese_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English burmese_finetuned_distilbert_portuguese DistilBertEmbeddings from jibi2906 +author: John Snow Labs +name: burmese_finetuned_distilbert_portuguese +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`burmese_finetuned_distilbert_portuguese` is a English model originally trained by jibi2906. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/burmese_finetuned_distilbert_portuguese_en_5.1.2_3.0_1694782684337.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/burmese_finetuned_distilbert_portuguese_en_5.1.2_3.0_1694782684337.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("burmese_finetuned_distilbert_portuguese","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("burmese_finetuned_distilbert_portuguese", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|burmese_finetuned_distilbert_portuguese| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jibi2906/my-finetuned-distilbert-pt \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-carrot_tuned_model_en.md b/docs/_posts/ahmedlone127/2023-09-15-carrot_tuned_model_en.md new file mode 100644 index 00000000000000..287a83bbc35942 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-carrot_tuned_model_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English carrot_tuned_model DistilBertEmbeddings from DaniloH +author: John Snow Labs +name: carrot_tuned_model +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`carrot_tuned_model` is a English model originally trained by DaniloH. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/carrot_tuned_model_en_5.1.2_3.0_1694781032170.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/carrot_tuned_model_en_5.1.2_3.0_1694781032170.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("carrot_tuned_model","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("carrot_tuned_model", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|carrot_tuned_model| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/DaniloH/carrot-tuned-model \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-clinical_bert_finetuned_en.md b/docs/_posts/ahmedlone127/2023-09-15-clinical_bert_finetuned_en.md new file mode 100644 index 00000000000000..f26d4c79c8962b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-clinical_bert_finetuned_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English clinical_bert_finetuned DistilBertEmbeddings from aminghias +author: John Snow Labs +name: clinical_bert_finetuned +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`clinical_bert_finetuned` is a English model originally trained by aminghias. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/clinical_bert_finetuned_en_5.1.2_3.0_1694784623028.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/clinical_bert_finetuned_en_5.1.2_3.0_1694784623028.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("clinical_bert_finetuned","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("clinical_bert_finetuned", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|clinical_bert_finetuned| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.3 MB| + +## References + +https://huggingface.co/aminghias/Clinical-BERT-finetuned \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-clinicalbert_medicalai_en.md b/docs/_posts/ahmedlone127/2023-09-15-clinicalbert_medicalai_en.md new file mode 100644 index 00000000000000..aa008cdd4f9abb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-clinicalbert_medicalai_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English clinicalbert_medicalai DistilBertEmbeddings from medicalai +author: John Snow Labs +name: clinicalbert_medicalai +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`clinicalbert_medicalai` is a English model originally trained by medicalai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/clinicalbert_medicalai_en_5.1.2_3.0_1694775464907.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/clinicalbert_medicalai_en_5.1.2_3.0_1694775464907.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("clinicalbert_medicalai","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("clinicalbert_medicalai", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|clinicalbert_medicalai| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.3 MB| + +## References + +https://huggingface.co/medicalai/ClinicalBERT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-clr_pretrained_distilbert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-clr_pretrained_distilbert_base_uncased_en.md new file mode 100644 index 00000000000000..33d06d45924af0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-clr_pretrained_distilbert_base_uncased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English clr_pretrained_distilbert_base_uncased DistilBertEmbeddings from SauravMaheshkar +author: John Snow Labs +name: clr_pretrained_distilbert_base_uncased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`clr_pretrained_distilbert_base_uncased` is a English model originally trained by SauravMaheshkar. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/clr_pretrained_distilbert_base_uncased_en_5.1.2_3.0_1694779351433.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/clr_pretrained_distilbert_base_uncased_en_5.1.2_3.0_1694779351433.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("clr_pretrained_distilbert_base_uncased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("clr_pretrained_distilbert_base_uncased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|clr_pretrained_distilbert_base_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/SauravMaheshkar/clr-pretrained-distilbert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-crypto_bert_model_en.md b/docs/_posts/ahmedlone127/2023-09-15-crypto_bert_model_en.md new file mode 100644 index 00000000000000..ab9953467ca37a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-crypto_bert_model_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English crypto_bert_model DistilBertEmbeddings from vedantgoswami +author: John Snow Labs +name: crypto_bert_model +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`crypto_bert_model` is a English model originally trained by vedantgoswami. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/crypto_bert_model_en_5.1.2_3.0_1694787260868.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/crypto_bert_model_en_5.1.2_3.0_1694787260868.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("crypto_bert_model","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("crypto_bert_model", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|crypto_bert_model| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|402.3 MB| + +## References + +https://huggingface.co/vedantgoswami/crypto-bert-model \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-customer_data_tuned_trial_1_en.md b/docs/_posts/ahmedlone127/2023-09-15-customer_data_tuned_trial_1_en.md new file mode 100644 index 00000000000000..de65fef610203f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-customer_data_tuned_trial_1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English customer_data_tuned_trial_1 DistilBertEmbeddings from EslamAhmed +author: John Snow Labs +name: customer_data_tuned_trial_1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`customer_data_tuned_trial_1` is a English model originally trained by EslamAhmed. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/customer_data_tuned_trial_1_en_5.1.2_3.0_1694770508030.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/customer_data_tuned_trial_1_en_5.1.2_3.0_1694770508030.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("customer_data_tuned_trial_1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("customer_data_tuned_trial_1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|customer_data_tuned_trial_1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|402.3 MB| + +## References + +https://huggingface.co/EslamAhmed/customer_data_tuned_trial_1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-dbert_finetuned_en.md b/docs/_posts/ahmedlone127/2023-09-15-dbert_finetuned_en.md new file mode 100644 index 00000000000000..f6124834e65b4d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-dbert_finetuned_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English dbert_finetuned DistilBertEmbeddings from ksabeh +author: John Snow Labs +name: dbert_finetuned +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`dbert_finetuned` is a English model originally trained by ksabeh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/dbert_finetuned_en_5.1.2_3.0_1694772576304.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/dbert_finetuned_en_5.1.2_3.0_1694772576304.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("dbert_finetuned","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("dbert_finetuned", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|dbert_finetuned| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ksabeh/dbert-finetuned \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-dbert_finetuned_g_en.md b/docs/_posts/ahmedlone127/2023-09-15-dbert_finetuned_g_en.md new file mode 100644 index 00000000000000..248dd699f61a0e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-dbert_finetuned_g_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English dbert_finetuned_g DistilBertEmbeddings from e-hossam96 +author: John Snow Labs +name: dbert_finetuned_g +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`dbert_finetuned_g` is a English model originally trained by e-hossam96. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/dbert_finetuned_g_en_5.1.2_3.0_1694775531375.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/dbert_finetuned_g_en_5.1.2_3.0_1694775531375.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("dbert_finetuned_g","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("dbert_finetuned_g", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|dbert_finetuned_g| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/e-hossam96/dbert-finetuned-g \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-dbert_rda_en.md b/docs/_posts/ahmedlone127/2023-09-15-dbert_rda_en.md new file mode 100644 index 00000000000000..2a5b3183080fd7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-dbert_rda_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English dbert_rda DistilBertEmbeddings from nkul +author: John Snow Labs +name: dbert_rda +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`dbert_rda` is a English model originally trained by nkul. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/dbert_rda_en_5.1.2_3.0_1694783312876.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/dbert_rda_en_5.1.2_3.0_1694783312876.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("dbert_rda","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("dbert_rda", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|dbert_rda| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/nkul/dbert-rda \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-debiasing_pre_trained_contextualised_embeddings_distil_bert_en.md b/docs/_posts/ahmedlone127/2023-09-15-debiasing_pre_trained_contextualised_embeddings_distil_bert_en.md index f7f40c0501d222..6073c0a320d86f 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-debiasing_pre_trained_contextualised_embeddings_distil_bert_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-debiasing_pre_trained_contextualised_embeddings_distil_bert_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/debiasing_pre_trained_contextualised_embeddings_distil_bert_en_5.1.2_3.0_1694736696151.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/debiasing_pre_trained_contextualised_embeddings_distil_bert_en_5.1.2_3.0_1694736696151.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/debiasing_pre_trained_contextualised_embeddings_distil_bert_en_5.1.2_3.0_1694770008501.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/debiasing_pre_trained_contextualised_embeddings_distil_bert_en_5.1.2_3.0_1694770008501.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distil_bert_aave_large_en.md b/docs/_posts/ahmedlone127/2023-09-15-distil_bert_aave_large_en.md new file mode 100644 index 00000000000000..fc36f7295e21c1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distil_bert_aave_large_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distil_bert_aave_large DistilBertEmbeddings from csalaam +author: John Snow Labs +name: distil_bert_aave_large +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distil_bert_aave_large` is a English model originally trained by csalaam. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distil_bert_aave_large_en_5.1.2_3.0_1694783341558.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distil_bert_aave_large_en_5.1.2_3.0_1694783341558.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distil_bert_aave_large","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distil_bert_aave_large", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distil_bert_aave_large| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.4 MB| + +## References + +https://huggingface.co/csalaam/distil-bert-aave-large \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distil_eng_en.md b/docs/_posts/ahmedlone127/2023-09-15-distil_eng_en.md new file mode 100644 index 00000000000000..81b436f220bfff --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distil_eng_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distil_eng DistilBertEmbeddings from mboth +author: John Snow Labs +name: distil_eng +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distil_eng` is a English model originally trained by mboth. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distil_eng_en_5.1.2_3.0_1694782258463.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distil_eng_en_5.1.2_3.0_1694782258463.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distil_eng","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distil_eng", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distil_eng| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.5 MB| + +## References + +https://huggingface.co/mboth/distil-eng \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_akuapem_twi_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_akuapem_twi_cased_en.md new file mode 100644 index 00000000000000..12589472a53379 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_akuapem_twi_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilabena_base_akuapem_twi_cased DistilBertEmbeddings from Ghana-NLP +author: John Snow Labs +name: distilabena_base_akuapem_twi_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilabena_base_akuapem_twi_cased` is a English model originally trained by Ghana-NLP. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilabena_base_akuapem_twi_cased_en_5.1.2_3.0_1694777845278.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilabena_base_akuapem_twi_cased_en_5.1.2_3.0_1694777845278.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilabena_base_akuapem_twi_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilabena_base_akuapem_twi_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilabena_base_akuapem_twi_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.3 MB| + +## References + +https://huggingface.co/Ghana-NLP/distilabena-base-akuapem-twi-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_asante_twi_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_asante_twi_uncased_en.md new file mode 100644 index 00000000000000..21f83b38462445 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_asante_twi_uncased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilabena_base_asante_twi_uncased DistilBertEmbeddings from Ghana-NLP +author: John Snow Labs +name: distilabena_base_asante_twi_uncased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilabena_base_asante_twi_uncased` is a English model originally trained by Ghana-NLP. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilabena_base_asante_twi_uncased_en_5.1.2_3.0_1694778027436.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilabena_base_asante_twi_uncased_en_5.1.2_3.0_1694778027436.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilabena_base_asante_twi_uncased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilabena_base_asante_twi_uncased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilabena_base_asante_twi_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.2 MB| + +## References + +https://huggingface.co/Ghana-NLP/distilabena-base-asante-twi-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_v2_akuapem_twi_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_v2_akuapem_twi_cased_en.md new file mode 100644 index 00000000000000..e4af1362a76f4f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_v2_akuapem_twi_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilabena_base_v2_akuapem_twi_cased DistilBertEmbeddings from Ghana-NLP +author: John Snow Labs +name: distilabena_base_v2_akuapem_twi_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilabena_base_v2_akuapem_twi_cased` is a English model originally trained by Ghana-NLP. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilabena_base_v2_akuapem_twi_cased_en_5.1.2_3.0_1694778202672.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilabena_base_v2_akuapem_twi_cased_en_5.1.2_3.0_1694778202672.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilabena_base_v2_akuapem_twi_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilabena_base_v2_akuapem_twi_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilabena_base_v2_akuapem_twi_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.0 MB| + +## References + +https://huggingface.co/Ghana-NLP/distilabena-base-v2-akuapem-twi-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_v2_asante_twi_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_v2_asante_twi_uncased_en.md new file mode 100644 index 00000000000000..6f00bae234db9b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilabena_base_v2_asante_twi_uncased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilabena_base_v2_asante_twi_uncased DistilBertEmbeddings from Ghana-NLP +author: John Snow Labs +name: distilabena_base_v2_asante_twi_uncased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilabena_base_v2_asante_twi_uncased` is a English model originally trained by Ghana-NLP. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilabena_base_v2_asante_twi_uncased_en_5.1.2_3.0_1694778363788.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilabena_base_v2_asante_twi_uncased_en_5.1.2_3.0_1694778363788.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilabena_base_v2_asante_twi_uncased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilabena_base_v2_asante_twi_uncased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilabena_base_v2_asante_twi_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.1 MB| + +## References + +https://huggingface.co/Ghana-NLP/distilabena-base-v2-asante-twi-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_add_pre_training_complete_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_add_pre_training_complete_en.md new file mode 100644 index 00000000000000..4df7e0415d31e4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_add_pre_training_complete_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_add_pre_training_complete DistilBertEmbeddings from gokuls +author: John Snow Labs +name: distilbert_add_pre_training_complete +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_add_pre_training_complete` is a English model originally trained by gokuls. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_add_pre_training_complete_en_5.1.2_3.0_1694788672681.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_add_pre_training_complete_en_5.1.2_3.0_1694788672681.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_add_pre_training_complete","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_add_pre_training_complete", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_add_pre_training_complete| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/gokuls/distilbert_add_pre-training-complete \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_add_pre_training_dim_96_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_add_pre_training_dim_96_en.md new file mode 100644 index 00000000000000..57c958c3c0f54c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_add_pre_training_dim_96_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_add_pre_training_dim_96 DistilBertEmbeddings from gokuls +author: John Snow Labs +name: distilbert_add_pre_training_dim_96 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_add_pre_training_dim_96` is a English model originally trained by gokuls. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_add_pre_training_dim_96_en_5.1.2_3.0_1694789132049.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_add_pre_training_dim_96_en_5.1.2_3.0_1694789132049.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_add_pre_training_dim_96","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_add_pre_training_dim_96", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_add_pre_training_dim_96| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|25.5 MB| + +## References + +https://huggingface.co/gokuls/distilbert_add_pre-training-dim-96 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_25lang_cased_xx.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_25lang_cased_xx.md new file mode 100644 index 00000000000000..c65abeb6e688bb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_25lang_cased_xx.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Multilingual distilbert_base_25lang_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_25lang_cased +date: 2023-09-15 +tags: [distilbert, xx, open_source, fill_mask, onnx] +task: Embeddings +language: xx +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_25lang_cased` is a Multilingual model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_25lang_cased_xx_5.1.2_3.0_1694771346236.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_25lang_cased_xx_5.1.2_3.0_1694771346236.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_25lang_cased","xx") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_25lang_cased", "xx") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_25lang_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|xx| +|Size:|405.6 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-25lang-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_cased_fine_tuned_blbooksgenre_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_cased_fine_tuned_blbooksgenre_en.md new file mode 100644 index 00000000000000..8f237f066a1f42 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_cased_fine_tuned_blbooksgenre_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_cased_fine_tuned_blbooksgenre DistilBertEmbeddings from BritishLibraryLabs +author: John Snow Labs +name: distilbert_base_cased_fine_tuned_blbooksgenre +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_cased_fine_tuned_blbooksgenre` is a English model originally trained by BritishLibraryLabs. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_cased_fine_tuned_blbooksgenre_en_5.1.2_3.0_1694777850511.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_cased_fine_tuned_blbooksgenre_en_5.1.2_3.0_1694777850511.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_cased_fine_tuned_blbooksgenre","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_cased_fine_tuned_blbooksgenre", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_cased_fine_tuned_blbooksgenre| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|243.7 MB| + +## References + +https://huggingface.co/BritishLibraryLabs/distilbert-base-cased-fine-tuned-blbooksgenre \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_arabic_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_arabic_cased_en.md new file mode 100644 index 00000000000000..d8b6aa20b2e8cd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_arabic_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_arabic_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_arabic_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_arabic_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_arabic_cased_en_5.1.2_3.0_1694771816351.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_arabic_cased_en_5.1.2_3.0_1694771816351.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_arabic_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_arabic_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_arabic_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|252.8 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-ar-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_bulgarian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_bulgarian_cased_en.md new file mode 100644 index 00000000000000..5f54413e5771a7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_bulgarian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_bulgarian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_bulgarian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_bulgarian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_bulgarian_cased_en_5.1.2_3.0_1694771936312.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_bulgarian_cased_en_5.1.2_3.0_1694771936312.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_bulgarian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_bulgarian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_bulgarian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|260.5 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-bg-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_chinese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_chinese_cased_en.md new file mode 100644 index 00000000000000..a2db36c483b540 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_chinese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_chinese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_chinese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_chinese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_chinese_cased_en_5.1.2_3.0_1694776185915.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_chinese_cased_en_5.1.2_3.0_1694776185915.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_chinese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_chinese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_chinese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|262.2 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-zh-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_chinese_hindi_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_chinese_hindi_cased_en.md new file mode 100644 index 00000000000000..415ac319d7a072 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_chinese_hindi_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_chinese_hindi_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_chinese_hindi_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_chinese_hindi_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_chinese_hindi_cased_en_5.1.2_3.0_1694776303232.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_chinese_hindi_cased_en_5.1.2_3.0_1694776303232.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_chinese_hindi_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_chinese_hindi_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_chinese_hindi_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|266.8 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-zh-hi-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_danish_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_danish_cased_en.md new file mode 100644 index 00000000000000..2d9e1196e841eb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_danish_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_danish_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_danish_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_danish_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_danish_cased_en_5.1.2_3.0_1694772113636.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_danish_cased_en_5.1.2_3.0_1694772113636.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_danish_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_danish_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_danish_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|255.0 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-da-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_dutch_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_dutch_cased_en.md new file mode 100644 index 00000000000000..61cb1497036289 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_dutch_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_dutch_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_dutch_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_dutch_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_dutch_cased_en_5.1.2_3.0_1694774832781.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_dutch_cased_en_5.1.2_3.0_1694774832781.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_dutch_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_dutch_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_dutch_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|256.4 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-nl-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_arabic_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_arabic_cased_en.md new file mode 100644 index 00000000000000..8f09ebf3492900 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_arabic_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_arabic_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_arabic_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_arabic_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_arabic_cased_en_5.1.2_3.0_1694772831618.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_arabic_cased_en_5.1.2_3.0_1694772831618.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_arabic_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_arabic_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_arabic_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|266.4 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-ar-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_cased_en.md new file mode 100644 index 00000000000000..f14dada027cdb0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_cased_en_5.1.2_3.0_1694772943858.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_cased_en_5.1.2_3.0_1694772943858.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|257.0 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_chinese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_chinese_cased_en.md new file mode 100644 index 00000000000000..36d70dc96125db --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_chinese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_chinese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_chinese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_chinese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_chinese_cased_en_5.1.2_3.0_1694774157815.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_chinese_cased_en_5.1.2_3.0_1694774157815.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_chinese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_chinese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_chinese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|275.7 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-zh-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_chinese_japanese_vietnamese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_chinese_japanese_vietnamese_cased_en.md new file mode 100644 index 00000000000000..0677b778b8aeb0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_chinese_japanese_vietnamese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_chinese_japanese_vietnamese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_chinese_japanese_vietnamese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_chinese_japanese_vietnamese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_chinese_japanese_vietnamese_cased_en_5.1.2_3.0_1694774268638.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_chinese_japanese_vietnamese_cased_en_5.1.2_3.0_1694774268638.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_chinese_japanese_vietnamese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_chinese_japanese_vietnamese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_chinese_japanese_vietnamese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|287.0 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-zh-ja-vi-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_danish_japanese_vietnamese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_danish_japanese_vietnamese_cased_en.md new file mode 100644 index 00000000000000..26ea43a59387ec --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_danish_japanese_vietnamese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_danish_japanese_vietnamese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_danish_japanese_vietnamese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_danish_japanese_vietnamese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_danish_japanese_vietnamese_cased_en_5.1.2_3.0_1694773081995.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_danish_japanese_vietnamese_cased_en_5.1.2_3.0_1694773081995.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_danish_japanese_vietnamese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_danish_japanese_vietnamese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_danish_japanese_vietnamese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|287.0 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-da-ja-vi-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_dutch_russian_arabic_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_dutch_russian_arabic_cased_en.md new file mode 100644 index 00000000000000..723c68a70aafef --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_dutch_russian_arabic_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_dutch_russian_arabic_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_dutch_russian_arabic_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_dutch_russian_arabic_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_dutch_russian_arabic_cased_en_5.1.2_3.0_1694774052258.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_dutch_russian_arabic_cased_en_5.1.2_3.0_1694774052258.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_dutch_russian_arabic_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_dutch_russian_arabic_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_dutch_russian_arabic_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|301.9 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-nl-ru-ar-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_german_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_german_cased_en.md new file mode 100644 index 00000000000000..9b3994bfcaa4ea --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_german_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_german_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_german_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_german_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_german_cased_en_5.1.2_3.0_1694773218512.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_german_cased_en_5.1.2_3.0_1694773218512.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_german_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_german_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_german_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|273.1 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-de-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_german_norwegian_danish_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_german_norwegian_danish_cased_en.md new file mode 100644 index 00000000000000..6f0459344ad57f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_german_norwegian_danish_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_german_norwegian_danish_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_german_norwegian_danish_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_german_norwegian_danish_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_german_norwegian_danish_cased_en_5.1.2_3.0_1694773335862.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_german_norwegian_danish_cased_en_5.1.2_3.0_1694773335862.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_german_norwegian_danish_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_german_norwegian_danish_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_german_norwegian_danish_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|280.9 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-de-no-da-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_italian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_italian_cased_en.md new file mode 100644 index 00000000000000..97d9954b4c2ee2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_italian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_italian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_italian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_italian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_italian_cased_en_5.1.2_3.0_1694773810141.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_italian_cased_en_5.1.2_3.0_1694773810141.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_italian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_italian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_italian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|268.6 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-it-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_lithuanian_norwegian_polish_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_lithuanian_norwegian_polish_cased_en.md new file mode 100644 index 00000000000000..bd6dc3c0e5832e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_lithuanian_norwegian_polish_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_lithuanian_norwegian_polish_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_lithuanian_norwegian_polish_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_lithuanian_norwegian_polish_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_lithuanian_norwegian_polish_cased_en_5.1.2_3.0_1694773937924.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_lithuanian_norwegian_polish_cased_en_5.1.2_3.0_1694773937924.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_lithuanian_norwegian_polish_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_lithuanian_norwegian_polish_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_lithuanian_norwegian_polish_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|282.3 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-lt-no-pl-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_cased_en.md new file mode 100644 index 00000000000000..d3d77074005313 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_spanish_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_spanish_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_spanish_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_spanish_cased_en_5.1.2_3.0_1694773457609.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_spanish_cased_en_5.1.2_3.0_1694773457609.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_spanish_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_spanish_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_spanish_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|273.5 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-es-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_german_chinese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_german_chinese_cased_en.md new file mode 100644 index 00000000000000..4c8ac82883c4a9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_german_chinese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_french_spanish_german_chinese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_spanish_german_chinese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_spanish_german_chinese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_spanish_german_chinese_cased_en_5.1.2_3.0_1694773578439.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_spanish_german_chinese_cased_en_5.1.2_3.0_1694773578439.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_spanish_german_chinese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_spanish_german_chinese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_spanish_german_chinese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|307.1 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-es-de-zh-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_portuguese_italian_cased_xx.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_portuguese_italian_cased_xx.md new file mode 100644 index 00000000000000..fb3d04ae622e55 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_french_spanish_portuguese_italian_cased_xx.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Multilingual distilbert_base_english_french_spanish_portuguese_italian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_french_spanish_portuguese_italian_cased +date: 2023-09-15 +tags: [distilbert, xx, open_source, fill_mask, onnx] +task: Embeddings +language: xx +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_french_spanish_portuguese_italian_cased` is a Multilingual model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_spanish_portuguese_italian_cased_xx_5.1.2_3.0_1694773689639.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_french_spanish_portuguese_italian_cased_xx_5.1.2_3.0_1694773689639.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_french_spanish_portuguese_italian_cased","xx") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_french_spanish_portuguese_italian_cased", "xx") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_french_spanish_portuguese_italian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|xx| +|Size:|285.0 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-fr-es-pt-it-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_german_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_german_cased_en.md new file mode 100644 index 00000000000000..f41b333cf9a22a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_german_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_german_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_german_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_german_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_german_cased_en_5.1.2_3.0_1694772216088.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_german_cased_en_5.1.2_3.0_1694772216088.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_german_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_german_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_german_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|262.2 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-de-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_hindi_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_hindi_cased_en.md new file mode 100644 index 00000000000000..e7019a696e680a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_hindi_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_hindi_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_hindi_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_hindi_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_hindi_cased_en_5.1.2_3.0_1694774382188.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_hindi_cased_en_5.1.2_3.0_1694774382188.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_hindi_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_hindi_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_hindi_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.4 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-hi-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_italian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_italian_cased_en.md new file mode 100644 index 00000000000000..586f8d76357949 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_italian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_italian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_italian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_italian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_italian_cased_en_5.1.2_3.0_1694774487693.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_italian_cased_en_5.1.2_3.0_1694774487693.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_italian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_italian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_italian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|258.3 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-it-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_japanese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_japanese_cased_en.md new file mode 100644 index 00000000000000..606d482826af62 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_japanese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_japanese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_japanese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_japanese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_japanese_cased_en_5.1.2_3.0_1694774608716.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_japanese_cased_en_5.1.2_3.0_1694774608716.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_japanese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_japanese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_japanese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|256.7 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-ja-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_lithuanian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_lithuanian_cased_en.md new file mode 100644 index 00000000000000..e40c9a0ef0a05d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_lithuanian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_lithuanian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_lithuanian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_lithuanian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_lithuanian_cased_en_5.1.2_3.0_1694774717030.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_lithuanian_cased_en_5.1.2_3.0_1694774717030.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_lithuanian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_lithuanian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_lithuanian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|252.4 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-lt-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_norwegian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_norwegian_cased_en.md new file mode 100644 index 00000000000000..fc156ef81deef1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_norwegian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_norwegian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_norwegian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_norwegian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_norwegian_cased_en_5.1.2_3.0_1694774950666.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_norwegian_cased_en_5.1.2_3.0_1694774950666.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_norwegian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_norwegian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_norwegian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|256.0 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-no-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_polish_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_polish_cased_en.md new file mode 100644 index 00000000000000..1c6551a361cb40 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_polish_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_polish_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_polish_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_polish_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_polish_cased_en_5.1.2_3.0_1694775064040.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_polish_cased_en_5.1.2_3.0_1694775064040.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_polish_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_polish_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_polish_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|258.3 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-pl-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_portuguese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_portuguese_cased_en.md new file mode 100644 index 00000000000000..66c1afe09eb274 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_portuguese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_portuguese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_portuguese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_portuguese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_portuguese_cased_en_5.1.2_3.0_1694775172152.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_portuguese_cased_en_5.1.2_3.0_1694775172152.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_portuguese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_portuguese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_portuguese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|259.6 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-pt-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_romanian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_romanian_cased_en.md new file mode 100644 index 00000000000000..16175fa13ef393 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_romanian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_romanian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_romanian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_romanian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_romanian_cased_en_5.1.2_3.0_1694775272352.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_romanian_cased_en_5.1.2_3.0_1694775272352.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_romanian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_romanian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_romanian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|253.7 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-ro-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_russian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_russian_cased_en.md new file mode 100644 index 00000000000000..7e6a1f9547a0c9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_russian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_russian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_russian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_russian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_russian_cased_en_5.1.2_3.0_1694775407575.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_russian_cased_en_5.1.2_3.0_1694775407575.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_russian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_russian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_russian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|268.7 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-ru-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_cased_en.md new file mode 100644 index 00000000000000..ac4013218ebf90 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_spanish_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_spanish_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_spanish_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_spanish_cased_en_5.1.2_3.0_1694772349323.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_spanish_cased_en_5.1.2_3.0_1694772349323.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_spanish_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_spanish_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_spanish_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|262.6 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-es-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_chinese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_chinese_cased_en.md new file mode 100644 index 00000000000000..de8fa75ccc422c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_chinese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_spanish_chinese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_spanish_chinese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_spanish_chinese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_spanish_chinese_cased_en_5.1.2_3.0_1694772709372.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_spanish_chinese_cased_en_5.1.2_3.0_1694772709372.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_spanish_chinese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_spanish_chinese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_spanish_chinese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|281.7 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-es-zh-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_italian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_italian_cased_en.md new file mode 100644 index 00000000000000..132dccba1d6e08 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_italian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_spanish_italian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_spanish_italian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_spanish_italian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_spanish_italian_cased_en_5.1.2_3.0_1694772463123.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_spanish_italian_cased_en_5.1.2_3.0_1694772463123.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_spanish_italian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_spanish_italian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_spanish_italian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|272.0 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-es-it-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_portuguese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_portuguese_cased_en.md new file mode 100644 index 00000000000000..e97b5e4fd7e93a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_spanish_portuguese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_spanish_portuguese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_spanish_portuguese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_spanish_portuguese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_spanish_portuguese_cased_en_5.1.2_3.0_1694772586206.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_spanish_portuguese_cased_en_5.1.2_3.0_1694772586206.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_spanish_portuguese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_spanish_portuguese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_spanish_portuguese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|268.4 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-es-pt-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_swahili_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_swahili_cased_en.md new file mode 100644 index 00000000000000..126f16b2350ba3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_swahili_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_swahili_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_swahili_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_swahili_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_swahili_cased_en_5.1.2_3.0_1694775528652.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_swahili_cased_en_5.1.2_3.0_1694775528652.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_swahili_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_swahili_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_swahili_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-sw-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_thai_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_thai_cased_en.md new file mode 100644 index 00000000000000..67daf96a0fd159 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_thai_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_thai_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_thai_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_thai_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_thai_cased_en_5.1.2_3.0_1694775652118.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_thai_cased_en_5.1.2_3.0_1694775652118.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_thai_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_thai_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_thai_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|244.7 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-th-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_turkish_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_turkish_cased_en.md new file mode 100644 index 00000000000000..ed2d8baf7aa504 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_turkish_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_turkish_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_turkish_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_turkish_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_turkish_cased_en_5.1.2_3.0_1694775755844.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_turkish_cased_en_5.1.2_3.0_1694775755844.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_turkish_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_turkish_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_turkish_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|251.1 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-tr-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_ukrainian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_ukrainian_cased_en.md new file mode 100644 index 00000000000000..86887587730333 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_ukrainian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_ukrainian_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_ukrainian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_ukrainian_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_ukrainian_cased_en_5.1.2_3.0_1694775863815.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_ukrainian_cased_en_5.1.2_3.0_1694775863815.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_ukrainian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_ukrainian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_ukrainian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|262.9 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-uk-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_urdu_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_urdu_cased_en.md new file mode 100644 index 00000000000000..f552acc2b40c20 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_urdu_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_urdu_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_urdu_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_urdu_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_urdu_cased_en_5.1.2_3.0_1694775970383.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_urdu_cased_en_5.1.2_3.0_1694775970383.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_urdu_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_urdu_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_urdu_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|251.1 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-ur-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_vietnamese_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_vietnamese_cased_en.md new file mode 100644 index 00000000000000..db1dac48cd374a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_english_vietnamese_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_english_vietnamese_cased DistilBertEmbeddings from Geotrend +author: John Snow Labs +name: distilbert_base_english_vietnamese_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_english_vietnamese_cased` is a English model originally trained by Geotrend. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_english_vietnamese_cased_en_5.1.2_3.0_1694776082127.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_english_vietnamese_cased_en_5.1.2_3.0_1694776082127.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_english_vietnamese_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_english_vietnamese_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_english_vietnamese_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|251.3 MB| + +## References + +https://huggingface.co/Geotrend/distilbert-base-en-vi-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_food_review_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_food_review_en.md new file mode 100644 index 00000000000000..e19e3205926823 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_food_review_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_food_review DistilBertEmbeddings from breakjl +author: John Snow Labs +name: distilbert_base_food_review +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_food_review` is a English model originally trained by breakjl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_food_review_en_5.1.2_3.0_1694781544212.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_food_review_en_5.1.2_3.0_1694781544212.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_food_review","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_food_review", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_food_review| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/breakjl/distilbert-base-food_review \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_german_cased_de.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_german_cased_de.md index cdb44bb6e9fe85..09b6d2a1fe6097 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_german_cased_de.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_german_cased_de.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_german_cased_de_5.1.2_3.0_1694736667910.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_german_cased_de_5.1.2_3.0_1694736667910.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_german_cased_de_5.1.2_3.0_1694769969382.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_german_cased_de_5.1.2_3.0_1694769969382.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_german_cased_finetuned_amazon_reviews_de.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_german_cased_finetuned_amazon_reviews_de.md new file mode 100644 index 00000000000000..ad8b9c47eb6bcd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_german_cased_finetuned_amazon_reviews_de.md @@ -0,0 +1,93 @@ +--- +layout: model +title: German distilbert_base_german_cased_finetuned_amazon_reviews DistilBertEmbeddings from mariav +author: John Snow Labs +name: distilbert_base_german_cased_finetuned_amazon_reviews +date: 2023-09-15 +tags: [distilbert, de, open_source, fill_mask, onnx] +task: Embeddings +language: de +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_german_cased_finetuned_amazon_reviews` is a German model originally trained by mariav. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_german_cased_finetuned_amazon_reviews_de_5.1.2_3.0_1694774283101.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_german_cased_finetuned_amazon_reviews_de_5.1.2_3.0_1694774283101.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_german_cased_finetuned_amazon_reviews","de") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_german_cased_finetuned_amazon_reviews", "de") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_german_cased_finetuned_amazon_reviews| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|de| +|Size:|250.3 MB| + +## References + +https://huggingface.co/mariav/distilbert-base-german-cased-finetuned-amazon-reviews \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_indonesian_id.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_indonesian_id.md new file mode 100644 index 00000000000000..6ffbb1a7dfb19c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_indonesian_id.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Indonesian distilbert_base_indonesian DistilBertEmbeddings from cahya +author: John Snow Labs +name: distilbert_base_indonesian +date: 2023-09-15 +tags: [distilbert, id, open_source, fill_mask, onnx] +task: Embeddings +language: id +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_indonesian` is a Indonesian model originally trained by cahya. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_indonesian_id_5.1.2_3.0_1694780162345.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_indonesian_id_5.1.2_3.0_1694780162345.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_indonesian","id") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_indonesian", "id") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_indonesian| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|id| +|Size:|253.0 MB| + +## References + +https://huggingface.co/cahya/distilbert-base-indonesian \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_multilingual_cased_bulgarian_wikipedia_xx.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_multilingual_cased_bulgarian_wikipedia_xx.md new file mode 100644 index 00000000000000..013ad0c084893a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_multilingual_cased_bulgarian_wikipedia_xx.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Multilingual distilbert_base_multilingual_cased_bulgarian_wikipedia DistilBertEmbeddings from mor40 +author: John Snow Labs +name: distilbert_base_multilingual_cased_bulgarian_wikipedia +date: 2023-09-15 +tags: [distilbert, xx, open_source, fill_mask, onnx] +task: Embeddings +language: xx +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_multilingual_cased_bulgarian_wikipedia` is a Multilingual model originally trained by mor40. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_multilingual_cased_bulgarian_wikipedia_xx_5.1.2_3.0_1694784992621.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_multilingual_cased_bulgarian_wikipedia_xx_5.1.2_3.0_1694784992621.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_multilingual_cased_bulgarian_wikipedia","xx") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_multilingual_cased_bulgarian_wikipedia", "xx") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_multilingual_cased_bulgarian_wikipedia| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|xx| +|Size:|505.3 MB| + +## References + +https://huggingface.co/mor40/distilbert-base-multilingual-cased-bg-wikipedia \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_multilingual_cased_finetuned_kintweetse_xx.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_multilingual_cased_finetuned_kintweetse_xx.md new file mode 100644 index 00000000000000..9205b7afab9408 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_multilingual_cased_finetuned_kintweetse_xx.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Multilingual distilbert_base_multilingual_cased_finetuned_kintweetse DistilBertEmbeddings from RogerB +author: John Snow Labs +name: distilbert_base_multilingual_cased_finetuned_kintweetse +date: 2023-09-15 +tags: [distilbert, xx, open_source, fill_mask, onnx] +task: Embeddings +language: xx +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_multilingual_cased_finetuned_kintweetse` is a Multilingual model originally trained by RogerB. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_multilingual_cased_finetuned_kintweetse_xx_5.1.2_3.0_1694773789090.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_multilingual_cased_finetuned_kintweetse_xx_5.1.2_3.0_1694773789090.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_multilingual_cased_finetuned_kintweetse","xx") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_multilingual_cased_finetuned_kintweetse", "xx") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_multilingual_cased_finetuned_kintweetse| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|xx| +|Size:|505.4 MB| + +## References + +https://huggingface.co/RogerB/distilbert-base-multilingual-cased-finetuned-kintweetsE \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_es.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_es.md new file mode 100644 index 00000000000000..c91d1b9b7089d4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_es.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Castilian, Spanish distilbert_base_spanish_uncased DistilBertEmbeddings from dccuchile +author: John Snow Labs +name: distilbert_base_spanish_uncased +date: 2023-09-15 +tags: [distilbert, es, open_source, fill_mask, onnx] +task: Embeddings +language: es +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_spanish_uncased` is a Castilian, Spanish model originally trained by dccuchile. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_spanish_uncased_es_5.1.2_3.0_1694770464754.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_spanish_uncased_es_5.1.2_3.0_1694770464754.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_spanish_uncased","es") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_spanish_uncased", "es") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_spanish_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|es| +|Size:|250.2 MB| + +## References + +https://huggingface.co/dccuchile/distilbert-base-spanish-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_finetuned_amazon_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_finetuned_amazon_en.md new file mode 100644 index 00000000000000..1a929d4ef1b1b0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_finetuned_amazon_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_spanish_uncased_finetuned_amazon DistilBertEmbeddings from Marianoleiras +author: John Snow Labs +name: distilbert_base_spanish_uncased_finetuned_amazon +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_spanish_uncased_finetuned_amazon` is a English model originally trained by Marianoleiras. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_spanish_uncased_finetuned_amazon_en_5.1.2_3.0_1694777013368.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_spanish_uncased_finetuned_amazon_en_5.1.2_3.0_1694777013368.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_spanish_uncased_finetuned_amazon","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_spanish_uncased_finetuned_amazon", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_spanish_uncased_finetuned_amazon| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|250.2 MB| + +## References + +https://huggingface.co/Marianoleiras/distilbert-base-spanish-uncased-finetuned-amazon \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_finetuned_clinais_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_finetuned_clinais_en.md new file mode 100644 index 00000000000000..2180d32468bab9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_finetuned_clinais_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_spanish_uncased_finetuned_clinais DistilBertEmbeddings from joheras +author: John Snow Labs +name: distilbert_base_spanish_uncased_finetuned_clinais +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_spanish_uncased_finetuned_clinais` is a English model originally trained by joheras. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_spanish_uncased_finetuned_clinais_en_5.1.2_3.0_1694774679930.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_spanish_uncased_finetuned_clinais_en_5.1.2_3.0_1694774679930.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_spanish_uncased_finetuned_clinais","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_spanish_uncased_finetuned_clinais", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_spanish_uncased_finetuned_clinais| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|250.2 MB| + +## References + +https://huggingface.co/joheras/distilbert-base-spanish-uncased-finetuned-clinais \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_model_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_model_en.md new file mode 100644 index 00000000000000..7154505408b50d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_spanish_uncased_model_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_spanish_uncased_model DistilBertEmbeddings from AleNunezArroyo +author: John Snow Labs +name: distilbert_base_spanish_uncased_model +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_spanish_uncased_model` is a English model originally trained by AleNunezArroyo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_spanish_uncased_model_en_5.1.2_3.0_1694786476451.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_spanish_uncased_model_en_5.1.2_3.0_1694786476451.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_spanish_uncased_model","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_spanish_uncased_model", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_spanish_uncased_model| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|250.2 MB| + +## References + +https://huggingface.co/AleNunezArroyo/distilbert-base-spanish-uncased-model \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_turkish_cased_offensive_mlm_tr.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_turkish_cased_offensive_mlm_tr.md new file mode 100644 index 00000000000000..73eaf8472f9710 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_turkish_cased_offensive_mlm_tr.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Turkish distilbert_base_turkish_cased_offensive_mlm DistilBertEmbeddings from Overfit-GM +author: John Snow Labs +name: distilbert_base_turkish_cased_offensive_mlm +date: 2023-09-15 +tags: [distilbert, tr, open_source, fill_mask, onnx] +task: Embeddings +language: tr +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_turkish_cased_offensive_mlm` is a Turkish model originally trained by Overfit-GM. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_offensive_mlm_tr_5.1.2_3.0_1694777986744.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_turkish_cased_offensive_mlm_tr_5.1.2_3.0_1694777986744.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_turkish_cased_offensive_mlm","tr") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_turkish_cased_offensive_mlm", "tr") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_turkish_cased_offensive_mlm| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|tr| +|Size:|251.8 MB| + +## References + +https://huggingface.co/Overfit-GM/distilbert-base-turkish-cased-offensive-mlm \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_aisera_texts_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_aisera_texts_en.md new file mode 100644 index 00000000000000..98e8bbc60c2f76 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_aisera_texts_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_aisera_texts DistilBertEmbeddings from Theimisa +author: John Snow Labs +name: distilbert_base_uncased_aisera_texts +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_aisera_texts` is a English model originally trained by Theimisa. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_aisera_texts_en_5.1.2_3.0_1694771537071.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_aisera_texts_en_5.1.2_3.0_1694771537071.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_aisera_texts","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_aisera_texts", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_aisera_texts| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Theimisa/distilbert-base-uncased-aisera_texts \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_aisera_texts_v3_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_aisera_texts_v3_en.md new file mode 100644 index 00000000000000..41c888ba9aa83a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_aisera_texts_v3_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_aisera_texts_v3 DistilBertEmbeddings from Theimisa +author: John Snow Labs +name: distilbert_base_uncased_aisera_texts_v3 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_aisera_texts_v3` is a English model originally trained by Theimisa. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_aisera_texts_v3_en_5.1.2_3.0_1694771955323.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_aisera_texts_v3_en_5.1.2_3.0_1694771955323.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_aisera_texts_v3","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_aisera_texts_v3", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_aisera_texts_v3| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Theimisa/distilbert-base-uncased-aisera_texts-v3 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_arxiv_abstracts_10k_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_arxiv_abstracts_10k_en.md new file mode 100644 index 00000000000000..244d68acd24e74 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_arxiv_abstracts_10k_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_arxiv_abstracts_10k DistilBertEmbeddings from timetoai +author: John Snow Labs +name: distilbert_base_uncased_arxiv_abstracts_10k +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_arxiv_abstracts_10k` is a English model originally trained by timetoai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_arxiv_abstracts_10k_en_5.1.2_3.0_1694786407387.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_arxiv_abstracts_10k_en_5.1.2_3.0_1694786407387.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_arxiv_abstracts_10k","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_arxiv_abstracts_10k", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_arxiv_abstracts_10k| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/timetoai/distilbert-base-uncased-arxiv-abstracts-10k \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_bert_yoga_finetuned_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_bert_yoga_finetuned_en.md new file mode 100644 index 00000000000000..dd84bcaf8d1de4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_bert_yoga_finetuned_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_bert_yoga_finetuned DistilBertEmbeddings from dsantistevan +author: John Snow Labs +name: distilbert_base_uncased_bert_yoga_finetuned +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_bert_yoga_finetuned` is a English model originally trained by dsantistevan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_bert_yoga_finetuned_en_5.1.2_3.0_1694782584370.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_bert_yoga_finetuned_en_5.1.2_3.0_1694782584370.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_bert_yoga_finetuned","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_bert_yoga_finetuned", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_bert_yoga_finetuned| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dsantistevan/distilbert-base-uncased-bert-yoga-finetuned \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_cohl_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_cohl_en.md new file mode 100644 index 00000000000000..20254050842eb7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_cohl_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_cohl DistilBertEmbeddings from shafin +author: John Snow Labs +name: distilbert_base_uncased_cohl +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_cohl` is a English model originally trained by shafin. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_cohl_en_5.1.2_3.0_1694789103082.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_cohl_en_5.1.2_3.0_1694789103082.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_cohl","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_cohl", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_cohl| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/shafin/distilbert-base-uncased-cohl \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned2_imdb_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned2_imdb_en.md index 288f7f544c168e..192a81712410a8 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned2_imdb_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned2_imdb_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned2_imdb_en_5.1.2_3.0_1694736806970.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned2_imdb_en_5.1.2_3.0_1694736806970.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned2_imdb_en_5.1.2_3.0_1694770185421.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned2_imdb_en_5.1.2_3.0_1694770185421.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_allocation_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_allocation_en.md new file mode 100644 index 00000000000000..408432551a1b7e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_allocation_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_allocation DistilBertEmbeddings from shubham7 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_allocation +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_allocation` is a English model originally trained by shubham7. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_allocation_en_5.1.2_3.0_1694789203683.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_allocation_en_5.1.2_3.0_1694789203683.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_allocation","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_allocation", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_allocation| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.4 MB| + +## References + +https://huggingface.co/shubham7/distilbert-base-uncased-finetuned-allocation \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_amazon_review_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_amazon_review_en.md new file mode 100644 index 00000000000000..61cd2d11f30b99 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_amazon_review_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_amazon_review DistilBertEmbeddings from soyisauce +author: John Snow Labs +name: distilbert_base_uncased_finetuned_amazon_review +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_amazon_review` is a English model originally trained by soyisauce. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_amazon_review_en_5.1.2_3.0_1694790068018.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_amazon_review_en_5.1.2_3.0_1694790068018.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_amazon_review","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_amazon_review", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_amazon_review| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/soyisauce/distilbert-base-uncased-finetuned-amazon_review \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ccnews_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ccnews_en.md new file mode 100644 index 00000000000000..c592f2cc267708 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ccnews_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_ccnews DistilBertEmbeddings from mchalek +author: John Snow Labs +name: distilbert_base_uncased_finetuned_ccnews +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_ccnews` is a English model originally trained by mchalek. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_ccnews_en_5.1.2_3.0_1694790900189.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_ccnews_en_5.1.2_3.0_1694790900189.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_ccnews","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_ccnews", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_ccnews| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mchalek/distilbert-base-uncased-finetuned-ccnews \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_en.md new file mode 100644 index 00000000000000..6a364cc025f64c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_char DistilBertEmbeddings from bhagasra-saurav +author: John Snow Labs +name: distilbert_base_uncased_finetuned_char +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_char` is a English model originally trained by bhagasra-saurav. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_char_en_5.1.2_3.0_1694784715338.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_char_en_5.1.2_3.0_1694784715338.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_char","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_char", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_char| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/bhagasra-saurav/distilbert-base-uncased-finetuned-char \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v1_en.md new file mode 100644 index 00000000000000..c2bd6fd8bcad8e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_char_v1 DistilBertEmbeddings from bhagasra-saurav +author: John Snow Labs +name: distilbert_base_uncased_finetuned_char_v1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_char_v1` is a English model originally trained by bhagasra-saurav. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_char_v1_en_5.1.2_3.0_1694785235023.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_char_v1_en_5.1.2_3.0_1694785235023.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_char_v1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_char_v1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_char_v1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/bhagasra-saurav/distilbert-base-uncased-finetuned-char-v1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v2_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v2_en.md new file mode 100644 index 00000000000000..66095204915f14 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v2_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_char_v2 DistilBertEmbeddings from bhagasra-saurav +author: John Snow Labs +name: distilbert_base_uncased_finetuned_char_v2 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_char_v2` is a English model originally trained by bhagasra-saurav. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_char_v2_en_5.1.2_3.0_1694785386613.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_char_v2_en_5.1.2_3.0_1694785386613.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_char_v2","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_char_v2", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_char_v2| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/bhagasra-saurav/distilbert-base-uncased-finetuned-char-v2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v3_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v3_en.md new file mode 100644 index 00000000000000..9224f204e3d4a5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_char_v3_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_char_v3 DistilBertEmbeddings from bhagasra-saurav +author: John Snow Labs +name: distilbert_base_uncased_finetuned_char_v3 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_char_v3` is a English model originally trained by bhagasra-saurav. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_char_v3_en_5.1.2_3.0_1694785507806.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_char_v3_en_5.1.2_3.0_1694785507806.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_char_v3","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_char_v3", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_char_v3| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/bhagasra-saurav/distilbert-base-uncased-finetuned-char-v3 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_civi_cooments_accelerate_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_civi_cooments_accelerate_en.md index bbe130d0a2833d..6849c3f4264606 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_civi_cooments_accelerate_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_civi_cooments_accelerate_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_civi_cooments_accelerate_en_5.1.2_3.0_1694736212479.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_civi_cooments_accelerate_en_5.1.2_3.0_1694736212479.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_civi_cooments_accelerate_en_5.1.2_3.0_1694772882674.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_civi_cooments_accelerate_en_5.1.2_3.0_1694772882674.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_clinc150_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_clinc150_en.md new file mode 100644 index 00000000000000..62008c1952d486 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_clinc150_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_clinc150 DistilBertEmbeddings from FilippoComastri +author: John Snow Labs +name: distilbert_base_uncased_finetuned_clinc150 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_clinc150` is a English model originally trained by FilippoComastri. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_clinc150_en_5.1.2_3.0_1694780894423.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_clinc150_en_5.1.2_3.0_1694780894423.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_clinc150","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_clinc150", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_clinc150| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/FilippoComastri/distilbert-base-uncased-finetuned-clinc150 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cnn_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cnn_en.md new file mode 100644 index 00000000000000..1dd8748f045f58 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cnn_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_cnn DistilBertEmbeddings from SmartPy +author: John Snow Labs +name: distilbert_base_uncased_finetuned_cnn +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_cnn` is a English model originally trained by SmartPy. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cnn_en_5.1.2_3.0_1694783567189.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cnn_en_5.1.2_3.0_1694783567189.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_cnn","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_cnn", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_cnn| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/SmartPy/distilbert-base-uncased-finetuned-cnn \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_crypto_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_crypto_en.md new file mode 100644 index 00000000000000..73aaf1d6d8970c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_crypto_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_crypto DistilBertEmbeddings from smarquie +author: John Snow Labs +name: distilbert_base_uncased_finetuned_crypto +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_crypto` is a English model originally trained by smarquie. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_crypto_en_5.1.2_3.0_1694780201008.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_crypto_en_5.1.2_3.0_1694780201008.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_crypto","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_crypto", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_crypto| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/smarquie/distilbert-base-uncased-finetuned-crypto \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ct_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ct_en.md new file mode 100644 index 00000000000000..00d315670b1fed --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ct_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_ct DistilBertEmbeddings from anthonyyazdani +author: John Snow Labs +name: distilbert_base_uncased_finetuned_ct +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_ct` is a English model originally trained by anthonyyazdani. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_ct_en_5.1.2_3.0_1694771385621.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_ct_en_5.1.2_3.0_1694771385621.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_ct","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_ct", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_ct| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/anthonyyazdani/distilbert-base-uncased-finetuned-CT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cust_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cust_en.md new file mode 100644 index 00000000000000..5ded3ab0043fd3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cust_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_cust DistilBertEmbeddings from shafin +author: John Snow Labs +name: distilbert_base_uncased_finetuned_cust +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_cust` is a English model originally trained by shafin. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cust_en_5.1.2_3.0_1694773996911.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cust_en_5.1.2_3.0_1694773996911.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_cust","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_cust", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_cust| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/shafin/distilbert-base-uncased-finetuned-cust \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cvent_2019_2022_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cvent_2019_2022_en.md index fc23d579765c5f..b85ccee1867399 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cvent_2019_2022_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cvent_2019_2022_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cvent_2019_2022_en_5.1.2_3.0_1694736129695.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cvent_2019_2022_en_5.1.2_3.0_1694736129695.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cvent_2019_2022_en_5.1.2_3.0_1694773096960.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cvent_2019_2022_en_5.1.2_3.0_1694773096960.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cvent_2022_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cvent_2022_en.md new file mode 100644 index 00000000000000..aa6933e92831f5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_cvent_2022_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_cvent_2022 DistilBertEmbeddings from vives +author: John Snow Labs +name: distilbert_base_uncased_finetuned_cvent_2022 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_cvent_2022` is a English model originally trained by vives. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cvent_2022_en_5.1.2_3.0_1694772739443.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_cvent_2022_en_5.1.2_3.0_1694772739443.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_cvent_2022","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_cvent_2022", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_cvent_2022| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/vives/distilbert-base-uncased-finetuned-cvent-2022 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_dis_mlm5_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_dis_mlm5_en.md new file mode 100644 index 00000000000000..76160242691f13 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_dis_mlm5_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_dis_mlm5 DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_dis_mlm5 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_dis_mlm5` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_dis_mlm5_en_5.1.2_3.0_1694781655821.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_dis_mlm5_en_5.1.2_3.0_1694781655821.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_dis_mlm5","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_dis_mlm5", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_dis_mlm5| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-DIS-mlm5 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_discord_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_discord_en.md new file mode 100644 index 00000000000000..8f57fc772ed09d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_discord_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_discord DistilBertEmbeddings from Phroggu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_discord +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_discord` is a English model originally trained by Phroggu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_discord_en_5.1.2_3.0_1694782495752.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_discord_en_5.1.2_3.0_1694782495752.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_discord","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_discord", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_discord| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Phroggu/distilbert-base-uncased-finetuned-discord \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_domain_adaptation_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_domain_adaptation_en.md new file mode 100644 index 00000000000000..b9678c9f78f3fa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_domain_adaptation_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_domain_adaptation DistilBertEmbeddings from algiraldohe +author: John Snow Labs +name: distilbert_base_uncased_finetuned_domain_adaptation +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_domain_adaptation` is a English model originally trained by algiraldohe. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_domain_adaptation_en_5.1.2_3.0_1694770565017.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_domain_adaptation_en_5.1.2_3.0_1694770565017.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_domain_adaptation","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_domain_adaptation", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_domain_adaptation| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/algiraldohe/distilbert-base-uncased-finetuned-domain-adaptation \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_fetch_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_fetch_en.md new file mode 100644 index 00000000000000..156d63873a6b60 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_fetch_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_fetch DistilBertEmbeddings from rtreptow +author: John Snow Labs +name: distilbert_base_uncased_finetuned_fetch +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_fetch` is a English model originally trained by rtreptow. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_fetch_en_5.1.2_3.0_1694792165514.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_fetch_en_5.1.2_3.0_1694792165514.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_fetch","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_fetch", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_fetch| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/rtreptow/distilbert-base-uncased-finetuned-fetch \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_game_accelerate_v2_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_game_accelerate_v2_en.md new file mode 100644 index 00000000000000..e7d87711bde367 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_game_accelerate_v2_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_game_accelerate_v2 DistilBertEmbeddings from kaiku03 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_game_accelerate_v2 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_game_accelerate_v2` is a English model originally trained by kaiku03. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_game_accelerate_v2_en_5.1.2_3.0_1694789931049.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_game_accelerate_v2_en_5.1.2_3.0_1694789931049.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_game_accelerate_v2","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_game_accelerate_v2", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_game_accelerate_v2| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/kaiku03/distilbert-base-uncased-finetuned-game-accelerate_V2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_en.md new file mode 100644 index 00000000000000..dce335a6e8a9d0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_himani_auto DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_himani_auto +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_himani_auto` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_en_5.1.2_3.0_1694780256193.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_en_5.1.2_3.0_1694780256193.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_himani_auto","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_himani_auto", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_himani_auto| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-himani_auto \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_gen_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_gen_en.md new file mode 100644 index 00000000000000..80b471a8a49cce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_gen_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_himani_auto_gen DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_himani_auto_gen +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_himani_auto_gen` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_gen_en_5.1.2_3.0_1694780783124.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_gen_en_5.1.2_3.0_1694780783124.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_himani_auto_gen","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_himani_auto_gen", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_himani_auto_gen| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-himani_auto-gen \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_text_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_text_en.md new file mode 100644 index 00000000000000..c24c8aa3930423 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_text_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_himani_auto_text DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_himani_auto_text +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_himani_auto_text` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_text_en_5.1.2_3.0_1694780380500.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_text_en_5.1.2_3.0_1694780380500.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_himani_auto_text","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_himani_auto_text", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_himani_auto_text| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-himani_auto-TEXT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_text_gen_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_text_gen_en.md new file mode 100644 index 00000000000000..764413b2f1274f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_text_gen_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_himani_auto_text_gen DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_himani_auto_text_gen +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_himani_auto_text_gen` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_text_gen_en_5.1.2_3.0_1694780620171.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_text_gen_en_5.1.2_3.0_1694780620171.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_himani_auto_text_gen","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_himani_auto_text_gen", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_himani_auto_text_gen| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-himani_auto-text-gen \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_textgeneration_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_textgeneration_en.md new file mode 100644 index 00000000000000..a2b0235a2c909f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_auto_textgeneration_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_himani_auto_textgeneration DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_himani_auto_textgeneration +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_himani_auto_textgeneration` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_textgeneration_en_5.1.2_3.0_1694780500428.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_auto_textgeneration_en_5.1.2_3.0_1694780500428.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_himani_auto_textgeneration","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_himani_auto_textgeneration", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_himani_auto_textgeneration| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-himani_auto-TEXTgeneration \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_gen_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_gen_en.md new file mode 100644 index 00000000000000..a4254b89309dad --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_gen_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_himani_gen DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_himani_gen +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_himani_gen` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_gen_en_5.1.2_3.0_1694780899595.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_gen_en_5.1.2_3.0_1694780899595.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_himani_gen","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_himani_gen", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_himani_gen| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-himani-gen \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_m_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_m_en.md new file mode 100644 index 00000000000000..8d3e1610cd4e11 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_himani_m_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_himani_m DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_himani_m +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_himani_m` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_m_en_5.1.2_3.0_1694781279459.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_himani_m_en_5.1.2_3.0_1694781279459.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_himani_m","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_himani_m", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_himani_m| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-himani-m \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_hina_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_hina_en.md new file mode 100644 index 00000000000000..3d3ce4fea0c69f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_hina_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_hina DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_hina +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_hina` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_hina_en_5.1.2_3.0_1694780144155.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_hina_en_5.1.2_3.0_1694780144155.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_hina","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_hina", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_hina| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-hina \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_homedepot_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_homedepot_en.md index e958f9e7829bd9..ee78b576460382 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_homedepot_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_homedepot_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_homedepot_en_5.1.2_3.0_1694736318696.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_homedepot_en_5.1.2_3.0_1694736318696.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_homedepot_en_5.1.2_3.0_1694773345195.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_homedepot_en_5.1.2_3.0_1694773345195.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_im_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_im_en.md new file mode 100644 index 00000000000000..60c44348217532 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_im_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_im DistilBertEmbeddings from shahriarebrampour +author: John Snow Labs +name: distilbert_base_uncased_finetuned_im +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_im` is a English model originally trained by shahriarebrampour. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_im_en_5.1.2_3.0_1694788569896.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_im_en_5.1.2_3.0_1694788569896.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_im","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_im", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_im| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/shahriarebrampour/distilbert-base-uncased-finetuned-im \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb1_en.md new file mode 100644 index 00000000000000..5126fed5979abf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb1 DistilBertEmbeddings from pulkitkumar13 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb1` is a English model originally trained by pulkitkumar13. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb1_en_5.1.2_3.0_1694787665201.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb1_en_5.1.2_3.0_1694787665201.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/pulkitkumar13/distilbert-base-uncased-finetuned-imdb1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_anikaai_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_anikaai_en.md new file mode 100644 index 00000000000000..85514f63f942d3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_anikaai_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_anikaai DistilBertEmbeddings from AnikaAI +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_anikaai +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_anikaai` is a English model originally trained by AnikaAI. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_anikaai_en_5.1.2_3.0_1694789143868.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_anikaai_en_5.1.2_3.0_1694789143868.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_anikaai","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_anikaai", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_anikaai| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/AnikaAI/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang_en.md new file mode 100644 index 00000000000000..bde3235d5932a5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang DistilBertEmbeddings from Arthuerwang +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang` is a English model originally trained by Arthuerwang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang_en_5.1.2_3.0_1694783071999.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang_en_5.1.2_3.0_1694783071999.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_arthuerwang| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Arthuerwang/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy_en.md new file mode 100644 index 00000000000000..45255bc0e2c683 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy DistilBertEmbeddings from averageandyyy +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy` is a English model originally trained by averageandyyy. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy_en_5.1.2_3.0_1694776377229.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy_en_5.1.2_3.0_1694776377229.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_averageandyyy| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/averageandyyy/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_binaryy_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_binaryy_en.md new file mode 100644 index 00000000000000..c4baa5b2af5634 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_binaryy_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_binaryy DistilBertEmbeddings from Binaryy +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_binaryy +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_binaryy` is a English model originally trained by Binaryy. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_binaryy_en_5.1.2_3.0_1694783198520.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_binaryy_en_5.1.2_3.0_1694783198520.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_binaryy","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_binaryy", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_binaryy| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Binaryy/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze_en.md new file mode 100644 index 00000000000000..9c83bd18214daf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze DistilBertEmbeddings from caroline-betbeze +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze` is a English model originally trained by caroline-betbeze. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze_en_5.1.2_3.0_1694782749314.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze_en_5.1.2_3.0_1694782749314.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_caroline_betbeze| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/caroline-betbeze/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_cchychen_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_cchychen_en.md new file mode 100644 index 00000000000000..382a9dbe2a65dd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_cchychen_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_cchychen DistilBertEmbeddings from Cchychen +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_cchychen +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_cchychen` is a English model originally trained by Cchychen. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_cchychen_en_5.1.2_3.0_1694786049897.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_cchychen_en_5.1.2_3.0_1694786049897.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_cchychen","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_cchychen", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_cchychen| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Cchychen/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh_en.md new file mode 100644 index 00000000000000..7c345712b2ccc1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh DistilBertEmbeddings from chenxingphh +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh` is a English model originally trained by chenxingphh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh_en_5.1.2_3.0_1694771845243.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh_en_5.1.2_3.0_1694771845243.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_chenxingphh| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/chenxingphh/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db_en.md new file mode 100644 index 00000000000000..334f5cd53e2113 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db DistilBertEmbeddings from coreyabs-db +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db` is a English model originally trained by coreyabs-db. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db_en_5.1.2_3.0_1694781387285.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db_en_5.1.2_3.0_1694781387285.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_coreyabs_db| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/coreyabs-db/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams_en.md new file mode 100644 index 00000000000000..be0d71be38ae57 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams DistilBertEmbeddings from DelusionalDreams +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams` is a English model originally trained by DelusionalDreams. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams_en_5.1.2_3.0_1694772163662.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams_en_5.1.2_3.0_1694772163662.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_delusionaldreams| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/DelusionalDreams/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_dewa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_dewa_en.md new file mode 100644 index 00000000000000..c8e5d61dfef8ed --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_dewa_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_dewa DistilBertEmbeddings from Dewa +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_dewa +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_dewa` is a English model originally trained by Dewa. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_dewa_en_5.1.2_3.0_1694777452620.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_dewa_en_5.1.2_3.0_1694777452620.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_dewa","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_dewa", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_dewa| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Dewa/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_dmlea_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_dmlea_en.md new file mode 100644 index 00000000000000..5b4fa23b7f93a0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_dmlea_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_dmlea DistilBertEmbeddings from dmlea +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_dmlea +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_dmlea` is a English model originally trained by dmlea. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_dmlea_en_5.1.2_3.0_1694790142387.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_dmlea_en_5.1.2_3.0_1694790142387.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_dmlea","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_dmlea", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_dmlea| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dmlea/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk_en.md new file mode 100644 index 00000000000000..3d028683b975b4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk DistilBertEmbeddings from elhamagk +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk` is a English model originally trained by elhamagk. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk_en_5.1.2_3.0_1694778234781.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk_en_5.1.2_3.0_1694778234781.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_elhamagk| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/elhamagk/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_emergix_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_emergix_en.md new file mode 100644 index 00000000000000..c314c1d6a4000e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_emergix_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_emergix DistilBertEmbeddings from emergix +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_emergix +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_emergix` is a English model originally trained by emergix. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_emergix_en_5.1.2_3.0_1694776509650.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_emergix_en_5.1.2_3.0_1694776509650.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_emergix","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_emergix", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_emergix| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/emergix/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_evincent18_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_evincent18_en.md new file mode 100644 index 00000000000000..6bf4a3c0e91d36 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_evincent18_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_evincent18 DistilBertEmbeddings from evincent18 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_evincent18 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_evincent18` is a English model originally trained by evincent18. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_evincent18_en_5.1.2_3.0_1694771587269.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_evincent18_en_5.1.2_3.0_1694771587269.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_evincent18","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_evincent18", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_evincent18| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/evincent18/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi_en.md new file mode 100644 index 00000000000000..197be0f2a3fb30 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi DistilBertEmbeddings from fadliaulawi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi` is a English model originally trained by fadliaulawi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi_en_5.1.2_3.0_1694775951105.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi_en_5.1.2_3.0_1694775951105.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_fadliaulawi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/fadliaulawi/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_francesc_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_francesc_en.md new file mode 100644 index 00000000000000..675ac5f986fe1b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_francesc_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_francesc DistilBertEmbeddings from Francesc +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_francesc +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_francesc` is a English model originally trained by Francesc. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_francesc_en_5.1.2_3.0_1694787169835.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_francesc_en_5.1.2_3.0_1694787169835.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_francesc","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_francesc", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_francesc| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Francesc/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ghost1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ghost1_en.md index 59397cf11b26c3..4220b4ef365618 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ghost1_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ghost1_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_ghost1_en_5.1.2_3.0_1694736935663.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_ghost1_en_5.1.2_3.0_1694736935663.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_ghost1_en_5.1.2_3.0_1694770280423.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_ghost1_en_5.1.2_3.0_1694770280423.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_golightly_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_golightly_en.md new file mode 100644 index 00000000000000..262d8869f48e30 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_golightly_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_golightly DistilBertEmbeddings from golightly +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_golightly +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_golightly` is a English model originally trained by golightly. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_golightly_en_5.1.2_3.0_1694790895420.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_golightly_en_5.1.2_3.0_1694790895420.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_golightly","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_golightly", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_golightly| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/golightly/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_gyronee_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_gyronee_en.md new file mode 100644 index 00000000000000..0a1097aa2f652b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_gyronee_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_gyronee DistilBertEmbeddings from gyronee +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_gyronee +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_gyronee` is a English model originally trained by gyronee. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_gyronee_en_5.1.2_3.0_1694778898355.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_gyronee_en_5.1.2_3.0_1694778898355.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_gyronee","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_gyronee", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_gyronee| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/gyronee/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira_en.md new file mode 100644 index 00000000000000..ddb2c158e6c39e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira DistilBertEmbeddings from hilariooliveira +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira` is a English model originally trained by hilariooliveira. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira_en_5.1.2_3.0_1694791662511.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira_en_5.1.2_3.0_1694791662511.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_hilariooliveira| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/hilariooliveira/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan_en.md new file mode 100644 index 00000000000000..78b51cd3e879dc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan DistilBertEmbeddings from hsiehpinghan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan` is a English model originally trained by hsiehpinghan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan_en_5.1.2_3.0_1694771644406.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan_en_5.1.2_3.0_1694771644406.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_hsiehpinghan| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/hsiehpinghan/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_icity_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_icity_en.md new file mode 100644 index 00000000000000..ed3134fc2b2935 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_icity_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_icity DistilBertEmbeddings from icity +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_icity +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_icity` is a English model originally trained by icity. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_icity_en_5.1.2_3.0_1694770827492.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_icity_en_5.1.2_3.0_1694770827492.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_icity","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_icity", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_icity| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/icity/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim_en.md new file mode 100644 index 00000000000000..b42c32039f9035 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim DistilBertEmbeddings from JakeYunwooKim +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim` is a English model originally trained by JakeYunwooKim. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim_en_5.1.2_3.0_1694786783189.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim_en_5.1.2_3.0_1694786783189.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_jakeyunwookim| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/JakeYunwooKim/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jcai1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jcai1_en.md new file mode 100644 index 00000000000000..e7b062a92e71a7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jcai1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_jcai1 DistilBertEmbeddings from jcai1 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_jcai1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_jcai1` is a English model originally trained by jcai1. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jcai1_en_5.1.2_3.0_1694771220693.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jcai1_en_5.1.2_3.0_1694771220693.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jcai1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jcai1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_jcai1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jcai1/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jdang_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jdang_en.md new file mode 100644 index 00000000000000..8a483e649a4d0a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jdang_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_jdang DistilBertEmbeddings from jdang +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_jdang +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_jdang` is a English model originally trained by jdang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jdang_en_5.1.2_3.0_1694778406635.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jdang_en_5.1.2_3.0_1694778406635.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jdang","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jdang", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_jdang| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jdang/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman_en.md new file mode 100644 index 00000000000000..ba8fc381e23e65 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman DistilBertEmbeddings from JJinBBangMan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman` is a English model originally trained by JJinBBangMan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman_en_5.1.2_3.0_1694787149226.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman_en_5.1.2_3.0_1694787149226.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_jjinbbangman| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/JJinBBangMan/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk_en.md new file mode 100644 index 00000000000000..920e66d668be9d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk DistilBertEmbeddings from johnyyhk +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk` is a English model originally trained by johnyyhk. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk_en_5.1.2_3.0_1694785389324.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk_en_5.1.2_3.0_1694785389324.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_johnyyhk| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/johnyyhk/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter_en.md new file mode 100644 index 00000000000000..d7c4c082430879 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter DistilBertEmbeddings from jordanblatter +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter` is a English model originally trained by jordanblatter. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter_en_5.1.2_3.0_1694783143004.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter_en_5.1.2_3.0_1694783143004.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_jordanblatter| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jordanblatter/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jwchung_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jwchung_en.md new file mode 100644 index 00000000000000..092eb224e14fc9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_jwchung_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_jwchung DistilBertEmbeddings from jwchung +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_jwchung +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_jwchung` is a English model originally trained by jwchung. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jwchung_en_5.1.2_3.0_1694774483686.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_jwchung_en_5.1.2_3.0_1694774483686.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jwchung","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_jwchung", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_jwchung| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jwchung/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825_en.md new file mode 100644 index 00000000000000..544093deb279cb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825 DistilBertEmbeddings from larryboy825 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825` is a English model originally trained by larryboy825. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825_en_5.1.2_3.0_1694775543945.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825_en_5.1.2_3.0_1694775543945.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_larryboy825| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/larryboy825/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_lewtun_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_lewtun_en.md new file mode 100644 index 00000000000000..b6851fc15b528a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_lewtun_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_lewtun DistilBertEmbeddings from lewtun +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_lewtun +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_lewtun` is a English model originally trained by lewtun. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_lewtun_en_5.1.2_3.0_1694781429360.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_lewtun_en_5.1.2_3.0_1694781429360.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_lewtun","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_lewtun", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_lewtun| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/lewtun/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_liquannan_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_liquannan_en.md new file mode 100644 index 00000000000000..45619a606744cb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_liquannan_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_liquannan DistilBertEmbeddings from liquannan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_liquannan +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_liquannan` is a English model originally trained by liquannan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_liquannan_en_5.1.2_3.0_1694770331398.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_liquannan_en_5.1.2_3.0_1694770331398.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_liquannan","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_liquannan", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_liquannan| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/liquannan/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_luzimu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_luzimu_en.md new file mode 100644 index 00000000000000..07af92acd37c4e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_luzimu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_luzimu DistilBertEmbeddings from luzimu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_luzimu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_luzimu` is a English model originally trained by luzimu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_luzimu_en_5.1.2_3.0_1694783067580.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_luzimu_en_5.1.2_3.0_1694783067580.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_luzimu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_luzimu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_luzimu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/luzimu/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013_en.md new file mode 100644 index 00000000000000..def64ecc5b5171 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013 DistilBertEmbeddings from lyk0013 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013` is a English model originally trained by lyk0013. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013_en_5.1.2_3.0_1694790463669.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013_en_5.1.2_3.0_1694790463669.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_lyk0013| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/lyk0013/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh_en.md new file mode 100644 index 00000000000000..a9542906b549d2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh DistilBertEmbeddings from magnustragardh +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh` is a English model originally trained by magnustragardh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh_en_5.1.2_3.0_1694784482897.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh_en_5.1.2_3.0_1694784482897.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_magnustragardh| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/magnustragardh/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8_en.md new file mode 100644 index 00000000000000..2b3e5da9589bc4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8 DistilBertEmbeddings from Mascariddu8 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8` is a English model originally trained by Mascariddu8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8_en_5.1.2_3.0_1694779288740.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8_en_5.1.2_3.0_1694779288740.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_mascariddu8| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Mascariddu8/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mbateman_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mbateman_en.md new file mode 100644 index 00000000000000..22a0f28c52b9a1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mbateman_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_mbateman DistilBertEmbeddings from mbateman +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_mbateman +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_mbateman` is a English model originally trained by mbateman. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_mbateman_en_5.1.2_3.0_1694781933141.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_mbateman_en_5.1.2_3.0_1694781933141.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_mbateman","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_mbateman", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_mbateman| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mbateman/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mulinski_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mulinski_en.md new file mode 100644 index 00000000000000..dd2d6c101a66db --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_mulinski_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_mulinski DistilBertEmbeddings from mulinski +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_mulinski +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_mulinski` is a English model originally trained by mulinski. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_mulinski_en_5.1.2_3.0_1694776279605.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_mulinski_en_5.1.2_3.0_1694776279605.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_mulinski","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_mulinski", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_mulinski| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mulinski/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri_en.md new file mode 100644 index 00000000000000..2775e40d77279a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri DistilBertEmbeddings from pavle-tsotskolauri +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri` is a English model originally trained by pavle-tsotskolauri. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri_en_5.1.2_3.0_1694771323246.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri_en_5.1.2_3.0_1694771323246.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_pavle_tsotskolauri| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/pavle-tsotskolauri/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu_en.md new file mode 100644 index 00000000000000..ebf6dd4c7409e5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu DistilBertEmbeddings from peterhsu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu` is a English model originally trained by peterhsu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu_en_5.1.2_3.0_1694783408621.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu_en_5.1.2_3.0_1694783408621.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_peterhsu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/peterhsu/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_physhunter_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_physhunter_en.md new file mode 100644 index 00000000000000..cf2aef600f03a9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_physhunter_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_physhunter DistilBertEmbeddings from PhysHunter +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_physhunter +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_physhunter` is a English model originally trained by PhysHunter. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_physhunter_en_5.1.2_3.0_1694773235874.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_physhunter_en_5.1.2_3.0_1694773235874.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_physhunter","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_physhunter", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_physhunter| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/PhysHunter/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88_en.md new file mode 100644 index 00000000000000..34649d44d2013b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88 DistilBertEmbeddings from qianyu88 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88` is a English model originally trained by qianyu88. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88_en_5.1.2_3.0_1694791575645.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88_en_5.1.2_3.0_1694791575645.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_qianyu88| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/qianyu88/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka_en.md new file mode 100644 index 00000000000000..da7a86034d5757 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka DistilBertEmbeddings from RajkNakka +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka` is a English model originally trained by RajkNakka. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka_en_5.1.2_3.0_1694789718500.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka_en_5.1.2_3.0_1694789718500.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_rajknakka| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/RajkNakka/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn_en.md new file mode 100644 index 00000000000000..ff062179b335a6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn DistilBertEmbeddings from rdvdsn +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn` is a English model originally trained by rdvdsn. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn_en_5.1.2_3.0_1694786749532.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn_en_5.1.2_3.0_1694786749532.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_rdvdsn| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/rdvdsn/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rugo_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rugo_en.md new file mode 100644 index 00000000000000..3958d058e5c25f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rugo_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_rugo DistilBertEmbeddings from rugo +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_rugo +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_rugo` is a English model originally trained by rugo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_rugo_en_5.1.2_3.0_1694783338406.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_rugo_en_5.1.2_3.0_1694783338406.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_rugo","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_rugo", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_rugo| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/rugo/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh_en.md new file mode 100644 index 00000000000000..f3ac492a2c078a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh DistilBertEmbeddings from Rushikesh +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh` is a English model originally trained by Rushikesh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh_en_5.1.2_3.0_1694782340471.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh_en_5.1.2_3.0_1694782340471.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_rushikesh| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Rushikesh/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai_en.md new file mode 100644 index 00000000000000..e5c2a2540731da --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai DistilBertEmbeddings from ryanlai +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai` is a English model originally trained by ryanlai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai_en_5.1.2_3.0_1694787087716.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai_en_5.1.2_3.0_1694787087716.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_ryanlai| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ryanlai/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44_en.md new file mode 100644 index 00000000000000..a6de82726a327b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44 DistilBertEmbeddings from sarthakc44 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44` is a English model originally trained by sarthakc44. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44_en_5.1.2_3.0_1694773431276.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44_en_5.1.2_3.0_1694773431276.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_sarthakc44| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/sarthakc44/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41_en.md new file mode 100644 index 00000000000000..5671f78b475aa1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41 DistilBertEmbeddings from ShadowTwin41 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41` is a English model originally trained by ShadowTwin41. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41_en_5.1.2_3.0_1694787894599.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41_en_5.1.2_3.0_1694787894599.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_shadowtwin41| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ShadowTwin41/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_spasis_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_spasis_en.md new file mode 100644 index 00000000000000..59dd4caf3680e9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_spasis_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_spasis DistilBertEmbeddings from spasis +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_spasis +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_spasis` is a English model originally trained by spasis. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_spasis_en_5.1.2_3.0_1694787046946.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_spasis_en_5.1.2_3.0_1694787046946.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_spasis","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_spasis", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_spasis| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/spasis/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71_en.md new file mode 100644 index 00000000000000..168ad312f748ca --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71 DistilBertEmbeddings from sungchun71 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71` is a English model originally trained by sungchun71. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71_en_5.1.2_3.0_1694774001255.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71_en_5.1.2_3.0_1694774001255.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_sungchun71| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/sungchun71/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_surjray_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_surjray_en.md new file mode 100644 index 00000000000000..50675e3b7168be --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_surjray_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_surjray DistilBertEmbeddings from surjray +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_surjray +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_surjray` is a English model originally trained by surjray. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_surjray_en_5.1.2_3.0_1694778413933.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_surjray_en_5.1.2_3.0_1694778413933.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_surjray","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_surjray", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_surjray| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/surjray/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_talhaa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_talhaa_en.md new file mode 100644 index 00000000000000..bb2995994b8b52 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_talhaa_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_talhaa DistilBertEmbeddings from talhaa +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_talhaa +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_talhaa` is a English model originally trained by talhaa. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_talhaa_en_5.1.2_3.0_1694786575831.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_talhaa_en_5.1.2_3.0_1694786575831.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_talhaa","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_talhaa", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_talhaa| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/talhaa/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan_en.md new file mode 100644 index 00000000000000..2f71074cd131bb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan DistilBertEmbeddings from tanvirkhan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan` is a English model originally trained by tanvirkhan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan_en_5.1.2_3.0_1694785375336.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan_en_5.1.2_3.0_1694785375336.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_tanvirkhan| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/tanvirkhan/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_terps_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_terps_en.md new file mode 100644 index 00000000000000..c0c74f701c926f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_terps_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_terps DistilBertEmbeddings from Terps +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_terps +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_terps` is a English model originally trained by Terps. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_terps_en_5.1.2_3.0_1694790594312.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_terps_en_5.1.2_3.0_1694790594312.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_terps","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_terps", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_terps| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Terps/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_thangvip_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_thangvip_en.md new file mode 100644 index 00000000000000..63313f6803eaca --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_thangvip_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_thangvip DistilBertEmbeddings from thangvip +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_thangvip +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_thangvip` is a English model originally trained by thangvip. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_thangvip_en_5.1.2_3.0_1694791316149.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_thangvip_en_5.1.2_3.0_1694791316149.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_thangvip","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_thangvip", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_thangvip| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/thangvip/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi_en.md new file mode 100644 index 00000000000000..2e448cb14dad75 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi DistilBertEmbeddings from ThetaPhiPsi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi` is a English model originally trained by ThetaPhiPsi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi_en_5.1.2_3.0_1694781360414.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi_en_5.1.2_3.0_1694781360414.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_thetaphipsi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ThetaPhiPsi/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_threite_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_threite_en.md new file mode 100644 index 00000000000000..3904d3683f92ec --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_threite_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_threite DistilBertEmbeddings from threite +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_threite +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_threite` is a English model originally trained by threite. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_threite_en_5.1.2_3.0_1694788276759.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_threite_en_5.1.2_3.0_1694788276759.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_threite","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_threite", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_threite| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/threite/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_timtl_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_timtl_en.md new file mode 100644 index 00000000000000..66aae5f7a59396 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_timtl_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_timtl DistilBertEmbeddings from TimTL +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_timtl +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_timtl` is a English model originally trained by TimTL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_timtl_en_5.1.2_3.0_1694787470542.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_timtl_en_5.1.2_3.0_1694787470542.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_timtl","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_timtl", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_timtl| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/TimTL/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama_en.md new file mode 100644 index 00000000000000..9f848af5608b19 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama DistilBertEmbeddings from tkoyama +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama` is a English model originally trained by tkoyama. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama_en_5.1.2_3.0_1694788742865.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama_en_5.1.2_3.0_1694788742865.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_tkoyama| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/tkoyama/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev_en.md new file mode 100644 index 00000000000000..8ea35a9d79670e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev DistilBertEmbeddings from tsobolev +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev` is a English model originally trained by tsobolev. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev_en_5.1.2_3.0_1694789508240.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev_en_5.1.2_3.0_1694789508240.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_tsobolev| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/tsobolev/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic_en.md new file mode 100644 index 00000000000000..51cdd81703037a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic DistilBertEmbeddings from ttmusic +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic` is a English model originally trained by ttmusic. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic_en_5.1.2_3.0_1694786680946.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic_en_5.1.2_3.0_1694786680946.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_ttmusic| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ttmusic/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_udoy_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_udoy_en.md new file mode 100644 index 00000000000000..ae85c58cf729ae --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_udoy_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_udoy DistilBertEmbeddings from Udoy +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_udoy +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_udoy` is a English model originally trained by Udoy. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_udoy_en_5.1.2_3.0_1694787044089.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_udoy_en_5.1.2_3.0_1694787044089.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_udoy","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_udoy", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_udoy| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Udoy/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan_en.md new file mode 100644 index 00000000000000..9e9e16648533d1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan DistilBertEmbeddings from VanHoan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan` is a English model originally trained by VanHoan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan_en_5.1.2_3.0_1694784218282.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan_en_5.1.2_3.0_1694784218282.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_vanhoan| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/VanHoan/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vives_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vives_en.md new file mode 100644 index 00000000000000..0fa2a9ebe6b44c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vives_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_vives DistilBertEmbeddings from vives +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_vives +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_vives` is a English model originally trained by vives. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_vives_en_5.1.2_3.0_1694772625562.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_vives_en_5.1.2_3.0_1694772625562.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_vives","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_vives", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_vives| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/vives/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas_en.md new file mode 100644 index 00000000000000..353f294c12a3b1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas DistilBertEmbeddings from vsrinivas +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas` is a English model originally trained by vsrinivas. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas_en_5.1.2_3.0_1694788081981.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas_en_5.1.2_3.0_1694788081981.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_vsrinivas| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/vsrinivas/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng_en.md new file mode 100644 index 00000000000000..f55dcf70c098ce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng DistilBertEmbeddings from wangmiaobeng +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng` is a English model originally trained by wangmiaobeng. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng_en_5.1.2_3.0_1694790638480.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng_en_5.1.2_3.0_1694790638480.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_wangmiaobeng| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/wangmiaobeng/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu_en.md new file mode 100644 index 00000000000000..62724f9be9198a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu DistilBertEmbeddings from WayneChiu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu` is a English model originally trained by WayneChiu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu_en_5.1.2_3.0_1694788869882.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu_en_5.1.2_3.0_1694788869882.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_waynechiu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/WayneChiu/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_winson_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_winson_en.md new file mode 100644 index 00000000000000..4769f7d193d153 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_winson_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_winson DistilBertEmbeddings from winson +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_winson +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_winson` is a English model originally trained by winson. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_winson_en_5.1.2_3.0_1694776770579.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_winson_en_5.1.2_3.0_1694776770579.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_winson","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_winson", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_winson| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/winson/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_xkang_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_xkang_en.md new file mode 100644 index 00000000000000..4e0213c75e57b7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_xkang_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_xkang DistilBertEmbeddings from xkang +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_xkang +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_xkang` is a English model originally trained by xkang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_xkang_en_5.1.2_3.0_1694785805536.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_xkang_en_5.1.2_3.0_1694785805536.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_xkang","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_xkang", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_xkang| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/xkang/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko_en.md new file mode 100644 index 00000000000000..4f460dbcbda848 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko DistilBertEmbeddings from yangwooko +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko` is a English model originally trained by yangwooko. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko_en_5.1.2_3.0_1694777159804.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko_en_5.1.2_3.0_1694777159804.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_yangwooko| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/yangwooko/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_yuto01_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_yuto01_en.md new file mode 100644 index 00000000000000..38b5cea503fb62 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_accelerate_yuto01_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_accelerate_yuto01 DistilBertEmbeddings from Yuto01 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_accelerate_yuto01 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_accelerate_yuto01` is a English model originally trained by Yuto01. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_yuto01_en_5.1.2_3.0_1694789597628.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_accelerate_yuto01_en_5.1.2_3.0_1694789597628.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_yuto01","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_accelerate_yuto01", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_accelerate_yuto01| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Yuto01/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_akashmaggon_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_akashmaggon_en.md new file mode 100644 index 00000000000000..d074260299e72b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_akashmaggon_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_akashmaggon DistilBertEmbeddings from akashmaggon +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_akashmaggon +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_akashmaggon` is a English model originally trained by akashmaggon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_akashmaggon_en_5.1.2_3.0_1694786916828.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_akashmaggon_en_5.1.2_3.0_1694786916828.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_akashmaggon","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_akashmaggon", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_akashmaggon| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/akashmaggon/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_akazad_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_akazad_en.md new file mode 100644 index 00000000000000..c92d705e708910 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_akazad_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_akazad DistilBertEmbeddings from akazad +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_akazad +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_akazad` is a English model originally trained by akazad. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_akazad_en_5.1.2_3.0_1694789344568.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_akazad_en_5.1.2_3.0_1694789344568.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_akazad","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_akazad", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_akazad| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/akazad/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_andrewr_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_andrewr_en.md new file mode 100644 index 00000000000000..6caaef76de79df --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_andrewr_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_andrewr DistilBertEmbeddings from AndrewR +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_andrewr +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_andrewr` is a English model originally trained by AndrewR. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_andrewr_en_5.1.2_3.0_1694790355579.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_andrewr_en_5.1.2_3.0_1694790355579.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_andrewr","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_andrewr", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_andrewr| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/AndrewR/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_anikaai_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_anikaai_en.md new file mode 100644 index 00000000000000..cd332606000491 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_anikaai_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_anikaai DistilBertEmbeddings from AnikaAI +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_anikaai +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_anikaai` is a English model originally trained by AnikaAI. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_anikaai_en_5.1.2_3.0_1694789041659.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_anikaai_en_5.1.2_3.0_1694789041659.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_anikaai","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_anikaai", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_anikaai| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/AnikaAI/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_anthonyyazdani_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_anthonyyazdani_en.md new file mode 100644 index 00000000000000..deccf083caa8ce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_anthonyyazdani_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_anthonyyazdani DistilBertEmbeddings from anthonyyazdani +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_anthonyyazdani +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_anthonyyazdani` is a English model originally trained by anthonyyazdani. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_anthonyyazdani_en_5.1.2_3.0_1694771270494.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_anthonyyazdani_en_5.1.2_3.0_1694771270494.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_anthonyyazdani","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_anthonyyazdani", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_anthonyyazdani| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/anthonyyazdani/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_aoill_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_aoill_en.md new file mode 100644 index 00000000000000..dee27866081dae --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_aoill_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_aoill DistilBertEmbeddings from aoill +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_aoill +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_aoill` is a English model originally trained by aoill. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_aoill_en_5.1.2_3.0_1694775321830.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_aoill_en_5.1.2_3.0_1694775321830.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_aoill","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_aoill", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_aoill| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/aoill/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_apatidar0_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_apatidar0_en.md new file mode 100644 index 00000000000000..5195f31d24a28d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_apatidar0_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_apatidar0 DistilBertEmbeddings from apatidar0 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_apatidar0 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_apatidar0` is a English model originally trained by apatidar0. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_apatidar0_en_5.1.2_3.0_1694789699531.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_apatidar0_en_5.1.2_3.0_1694789699531.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_apatidar0","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_apatidar0", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_apatidar0| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/apatidar0/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arjun9689_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arjun9689_en.md new file mode 100644 index 00000000000000..c07f8a4f293a7e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arjun9689_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_arjun9689 DistilBertEmbeddings from arjun9689 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_arjun9689 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_arjun9689` is a English model originally trained by arjun9689. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_arjun9689_en_5.1.2_3.0_1694777211475.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_arjun9689_en_5.1.2_3.0_1694777211475.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_arjun9689","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_arjun9689", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_arjun9689| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/arjun9689/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arthuerwang_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arthuerwang_en.md new file mode 100644 index 00000000000000..c58b8fd2284322 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arthuerwang_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_arthuerwang DistilBertEmbeddings from Arthuerwang +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_arthuerwang +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_arthuerwang` is a English model originally trained by Arthuerwang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_arthuerwang_en_5.1.2_3.0_1694782618860.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_arthuerwang_en_5.1.2_3.0_1694782618860.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_arthuerwang","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_arthuerwang", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_arthuerwang| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Arthuerwang/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arunadiraju_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arunadiraju_en.md new file mode 100644 index 00000000000000..665da3a304af55 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_arunadiraju_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_arunadiraju DistilBertEmbeddings from arunadiraju +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_arunadiraju +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_arunadiraju` is a English model originally trained by arunadiraju. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_arunadiraju_en_5.1.2_3.0_1694779661933.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_arunadiraju_en_5.1.2_3.0_1694779661933.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_arunadiraju","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_arunadiraju", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_arunadiraju| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/arunadiraju/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_at2507_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_at2507_en.md new file mode 100644 index 00000000000000..e3722b6b69c050 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_at2507_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_at2507 DistilBertEmbeddings from at2507 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_at2507 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_at2507` is a English model originally trained by at2507. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_at2507_en_5.1.2_3.0_1694772852025.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_at2507_en_5.1.2_3.0_1694772852025.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_at2507","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_at2507", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_at2507| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/at2507/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_atiiisham988_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_atiiisham988_en.md new file mode 100644 index 00000000000000..06e68f572a0e5a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_atiiisham988_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_atiiisham988 DistilBertEmbeddings from atiiisham988 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_atiiisham988 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_atiiisham988` is a English model originally trained by atiiisham988. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_atiiisham988_en_5.1.2_3.0_1694772504810.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_atiiisham988_en_5.1.2_3.0_1694772504810.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_atiiisham988","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_atiiisham988", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_atiiisham988| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/atiiisham988/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_averageandyyy_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_averageandyyy_en.md new file mode 100644 index 00000000000000..c785d4e81bc0c5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_averageandyyy_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_averageandyyy DistilBertEmbeddings from averageandyyy +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_averageandyyy +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_averageandyyy` is a English model originally trained by averageandyyy. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_averageandyyy_en_5.1.2_3.0_1694776247161.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_averageandyyy_en_5.1.2_3.0_1694776247161.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_averageandyyy","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_averageandyyy", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_averageandyyy| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/averageandyyy/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_bigearhututu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_bigearhututu_en.md new file mode 100644 index 00000000000000..8be5c1fca2c171 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_bigearhututu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_bigearhututu DistilBertEmbeddings from bigearhututu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_bigearhututu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_bigearhututu` is a English model originally trained by bigearhututu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_bigearhututu_en_5.1.2_3.0_1694775113143.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_bigearhututu_en_5.1.2_3.0_1694775113143.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_bigearhututu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_bigearhututu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_bigearhututu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/bigearhututu/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_brenton_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_brenton_en.md new file mode 100644 index 00000000000000..882b5cfb3e4a5b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_brenton_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_brenton DistilBertEmbeddings from brenton +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_brenton +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_brenton` is a English model originally trained by brenton. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_brenton_en_5.1.2_3.0_1694787537664.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_brenton_en_5.1.2_3.0_1694787537664.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_brenton","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_brenton", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_brenton| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/brenton/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_bubblejoe_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_bubblejoe_en.md new file mode 100644 index 00000000000000..95708a24fcafd8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_bubblejoe_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_bubblejoe DistilBertEmbeddings from BubbleJoe +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_bubblejoe +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_bubblejoe` is a English model originally trained by BubbleJoe. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_bubblejoe_en_5.1.2_3.0_1694782227859.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_bubblejoe_en_5.1.2_3.0_1694782227859.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_bubblejoe","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_bubblejoe", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_bubblejoe| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/BubbleJoe/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_caroline_betbeze_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_caroline_betbeze_en.md new file mode 100644 index 00000000000000..757fdc53be5b41 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_caroline_betbeze_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_caroline_betbeze DistilBertEmbeddings from caroline-betbeze +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_caroline_betbeze +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_caroline_betbeze` is a English model originally trained by caroline-betbeze. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_caroline_betbeze_en_5.1.2_3.0_1694782648414.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_caroline_betbeze_en_5.1.2_3.0_1694782648414.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_caroline_betbeze","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_caroline_betbeze", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_caroline_betbeze| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/caroline-betbeze/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cartinoe5930_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cartinoe5930_en.md new file mode 100644 index 00000000000000..e859e17b692462 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cartinoe5930_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_cartinoe5930 DistilBertEmbeddings from Cartinoe5930 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_cartinoe5930 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_cartinoe5930` is a English model originally trained by Cartinoe5930. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cartinoe5930_en_5.1.2_3.0_1694784085673.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cartinoe5930_en_5.1.2_3.0_1694784085673.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_cartinoe5930","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_cartinoe5930", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_cartinoe5930| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Cartinoe5930/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cchychen_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cchychen_en.md new file mode 100644 index 00000000000000..cf78c891438e85 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cchychen_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_cchychen DistilBertEmbeddings from Cchychen +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_cchychen +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_cchychen` is a English model originally trained by Cchychen. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cchychen_en_5.1.2_3.0_1694786158859.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cchychen_en_5.1.2_3.0_1694786158859.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_cchychen","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_cchychen", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_cchychen| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Cchychen/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_chenxingphh_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_chenxingphh_en.md new file mode 100644 index 00000000000000..14a89ef3a0f937 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_chenxingphh_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_chenxingphh DistilBertEmbeddings from chenxingphh +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_chenxingphh +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_chenxingphh` is a English model originally trained by chenxingphh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_chenxingphh_en_5.1.2_3.0_1694771729067.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_chenxingphh_en_5.1.2_3.0_1694771729067.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_chenxingphh","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_chenxingphh", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_chenxingphh| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/chenxingphh/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cindymc_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cindymc_en.md new file mode 100644 index 00000000000000..64f068843d732a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cindymc_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_cindymc DistilBertEmbeddings from cindymc +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_cindymc +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_cindymc` is a English model originally trained by cindymc. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cindymc_en_5.1.2_3.0_1694786805038.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cindymc_en_5.1.2_3.0_1694786805038.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_cindymc","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_cindymc", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_cindymc| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/cindymc/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cl_wood_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cl_wood_en.md new file mode 100644 index 00000000000000..5ce33cfc4167bf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cl_wood_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_cl_wood DistilBertEmbeddings from cl-wood +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_cl_wood +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_cl_wood` is a English model originally trained by cl-wood. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cl_wood_en_5.1.2_3.0_1694770937006.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cl_wood_en_5.1.2_3.0_1694770937006.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_cl_wood","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_cl_wood", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_cl_wood| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/cl-wood/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cleandata_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cleandata_en.md new file mode 100644 index 00000000000000..038ccccc225a70 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cleandata_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_cleandata DistilBertEmbeddings from cleandata +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_cleandata +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_cleandata` is a English model originally trained by cleandata. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cleandata_en_5.1.2_3.0_1694787303361.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cleandata_en_5.1.2_3.0_1694787303361.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_cleandata","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_cleandata", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_cleandata| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/cleandata/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_codeplay_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_codeplay_en.md new file mode 100644 index 00000000000000..65603cc5098af2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_codeplay_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_codeplay DistilBertEmbeddings from codeplay +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_codeplay +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_codeplay` is a English model originally trained by codeplay. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_codeplay_en_5.1.2_3.0_1694787263429.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_codeplay_en_5.1.2_3.0_1694787263429.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_codeplay","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_codeplay", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_codeplay| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/codeplay/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_coreyabs_db_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_coreyabs_db_en.md new file mode 100644 index 00000000000000..4d0585f4f3aa94 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_coreyabs_db_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_coreyabs_db DistilBertEmbeddings from coreyabs-db +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_coreyabs_db +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_coreyabs_db` is a English model originally trained by coreyabs-db. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_coreyabs_db_en_5.1.2_3.0_1694781268724.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_coreyabs_db_en_5.1.2_3.0_1694781268724.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_coreyabs_db","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_coreyabs_db", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_coreyabs_db| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/coreyabs-db/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cssupport_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cssupport_en.md new file mode 100644 index 00000000000000..8b1b618b1fe744 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_cssupport_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_cssupport DistilBertEmbeddings from cssupport +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_cssupport +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_cssupport` is a English model originally trained by cssupport. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cssupport_en_5.1.2_3.0_1694781174746.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_cssupport_en_5.1.2_3.0_1694781174746.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_cssupport","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_cssupport", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_cssupport| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/cssupport/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dave_sheets_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dave_sheets_en.md new file mode 100644 index 00000000000000..6f5258d356e46f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dave_sheets_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_dave_sheets DistilBertEmbeddings from Dave-Sheets +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_dave_sheets +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_dave_sheets` is a English model originally trained by Dave-Sheets. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dave_sheets_en_5.1.2_3.0_1694774885308.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dave_sheets_en_5.1.2_3.0_1694774885308.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_dave_sheets","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_dave_sheets", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_dave_sheets| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Dave-Sheets/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_debug_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_debug_en.md new file mode 100644 index 00000000000000..1c2260c9ed02fa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_debug_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_debug DistilBertEmbeddings from lewtun +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_debug +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_debug` is a English model originally trained by lewtun. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_debug_en_5.1.2_3.0_1694785359537.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_debug_en_5.1.2_3.0_1694785359537.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_debug","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_debug", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_debug| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/lewtun/distilbert-base-uncased-finetuned-imdb-debug \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_delusionaldreams_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_delusionaldreams_en.md new file mode 100644 index 00000000000000..30583928480413 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_delusionaldreams_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_delusionaldreams DistilBertEmbeddings from DelusionalDreams +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_delusionaldreams +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_delusionaldreams` is a English model originally trained by DelusionalDreams. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_delusionaldreams_en_5.1.2_3.0_1694772062647.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_delusionaldreams_en_5.1.2_3.0_1694772062647.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_delusionaldreams","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_delusionaldreams", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_delusionaldreams| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/DelusionalDreams/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dewa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dewa_en.md new file mode 100644 index 00000000000000..f0bf012d043671 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dewa_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_dewa DistilBertEmbeddings from Dewa +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_dewa +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_dewa` is a English model originally trained by Dewa. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dewa_en_5.1.2_3.0_1694777331208.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dewa_en_5.1.2_3.0_1694777331208.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_dewa","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_dewa", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_dewa| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Dewa/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dieexbr_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dieexbr_en.md new file mode 100644 index 00000000000000..c0fc37a5751a9a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dieexbr_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_dieexbr DistilBertEmbeddings from dieexbr +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_dieexbr +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_dieexbr` is a English model originally trained by dieexbr. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dieexbr_en_5.1.2_3.0_1694771700734.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dieexbr_en_5.1.2_3.0_1694771700734.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_dieexbr","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_dieexbr", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_dieexbr| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dieexbr/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dipika09_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dipika09_en.md new file mode 100644 index 00000000000000..9454ae3c2c31f5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dipika09_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_dipika09 DistilBertEmbeddings from Dipika09 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_dipika09 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_dipika09` is a English model originally trained by Dipika09. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dipika09_en_5.1.2_3.0_1694789723756.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dipika09_en_5.1.2_3.0_1694789723756.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_dipika09","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_dipika09", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_dipika09| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Dipika09/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dmlea_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dmlea_en.md new file mode 100644 index 00000000000000..bcc0834ba821ab --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dmlea_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_dmlea DistilBertEmbeddings from dmlea +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_dmlea +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_dmlea` is a English model originally trained by dmlea. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dmlea_en_5.1.2_3.0_1694790044524.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dmlea_en_5.1.2_3.0_1694790044524.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_dmlea","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_dmlea", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_dmlea| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dmlea/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_drdspace_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_drdspace_en.md new file mode 100644 index 00000000000000..dbd7a7611ec4b5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_drdspace_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_drdspace DistilBertEmbeddings from drdspace +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_drdspace +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_drdspace` is a English model originally trained by drdspace. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_drdspace_en_5.1.2_3.0_1694783734326.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_drdspace_en_5.1.2_3.0_1694783734326.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_drdspace","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_drdspace", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_drdspace| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/drdspace/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dshvetsov_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dshvetsov_en.md new file mode 100644 index 00000000000000..855ea38f4559aa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_dshvetsov_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_dshvetsov DistilBertEmbeddings from dshvetsov +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_dshvetsov +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_dshvetsov` is a English model originally trained by dshvetsov. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dshvetsov_en_5.1.2_3.0_1694782739474.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_dshvetsov_en_5.1.2_3.0_1694782739474.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_dshvetsov","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_dshvetsov", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_dshvetsov| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dshvetsov/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ecosystem_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ecosystem_en.md new file mode 100644 index 00000000000000..4f12510ac207f2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ecosystem_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_ecosystem DistilBertEmbeddings from ecosystem +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_ecosystem +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_ecosystem` is a English model originally trained by ecosystem. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_ecosystem_en_5.1.2_3.0_1694776959436.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_ecosystem_en_5.1.2_3.0_1694776959436.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_ecosystem","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_ecosystem", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_ecosystem| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ecosystem/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_edraper88_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_edraper88_en.md new file mode 100644 index 00000000000000..7f067a64f33b16 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_edraper88_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_edraper88 DistilBertEmbeddings from edraper88 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_edraper88 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_edraper88` is a English model originally trained by edraper88. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_edraper88_en_5.1.2_3.0_1694791144038.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_edraper88_en_5.1.2_3.0_1694791144038.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_edraper88","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_edraper88", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_edraper88| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/edraper88/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_eitanli_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_eitanli_en.md new file mode 100644 index 00000000000000..7b9b7ffbf63ba6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_eitanli_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_eitanli DistilBertEmbeddings from Eitanli +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_eitanli +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_eitanli` is a English model originally trained by Eitanli. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_eitanli_en_5.1.2_3.0_1694785816192.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_eitanli_en_5.1.2_3.0_1694785816192.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_eitanli","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_eitanli", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_eitanli| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Eitanli/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_elggman_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_elggman_en.md new file mode 100644 index 00000000000000..6fc02e83c10865 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_elggman_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_elggman DistilBertEmbeddings from ELggman +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_elggman +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_elggman` is a English model originally trained by ELggman. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_elggman_en_5.1.2_3.0_1694784844116.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_elggman_en_5.1.2_3.0_1694784844116.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_elggman","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_elggman", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_elggman| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ELggman/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_eusojk_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_eusojk_en.md new file mode 100644 index 00000000000000..e4096b978b26cc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_eusojk_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_eusojk DistilBertEmbeddings from eusojk +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_eusojk +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_eusojk` is a English model originally trained by eusojk. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_eusojk_en_5.1.2_3.0_1694784211104.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_eusojk_en_5.1.2_3.0_1694784211104.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_eusojk","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_eusojk", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_eusojk| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/eusojk/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_evincent18_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_evincent18_en.md new file mode 100644 index 00000000000000..fcf7eb07b7d19d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_evincent18_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_evincent18 DistilBertEmbeddings from evincent18 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_evincent18 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_evincent18` is a English model originally trained by evincent18. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_evincent18_en_5.1.2_3.0_1694771481378.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_evincent18_en_5.1.2_3.0_1694771481378.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_evincent18","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_evincent18", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_evincent18| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/evincent18/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_fadliaulawi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_fadliaulawi_en.md new file mode 100644 index 00000000000000..23f3b87d5a0281 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_fadliaulawi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_fadliaulawi DistilBertEmbeddings from fadliaulawi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_fadliaulawi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_fadliaulawi` is a English model originally trained by fadliaulawi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_fadliaulawi_en_5.1.2_3.0_1694775718136.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_fadliaulawi_en_5.1.2_3.0_1694775718136.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_fadliaulawi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_fadliaulawi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_fadliaulawi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/fadliaulawi/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_feeeper_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_feeeper_en.md new file mode 100644 index 00000000000000..e1ef4d25ccb1a5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_feeeper_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_feeeper DistilBertEmbeddings from feeeper +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_feeeper +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_feeeper` is a English model originally trained by feeeper. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_feeeper_en_5.1.2_3.0_1694778391045.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_feeeper_en_5.1.2_3.0_1694778391045.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_feeeper","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_feeeper", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_feeeper| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/feeeper/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin_en.md new file mode 100644 index 00000000000000..2e0723b6dccd75 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin DistilBertEmbeddings from chenyanjin +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin` is a English model originally trained by chenyanjin. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin_en_5.1.2_3.0_1694783843728.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin_en_5.1.2_3.0_1694783843728.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_finetuned_imdb_chenyanjin| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/chenyanjin/distilbert-base-uncased-finetuned-imdb-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_geolearner_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_geolearner_en.md new file mode 100644 index 00000000000000..52165837706ebe --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_geolearner_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_geolearner DistilBertEmbeddings from geolearner +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_geolearner +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_geolearner` is a English model originally trained by geolearner. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_geolearner_en_5.1.2_3.0_1694776548569.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_geolearner_en_5.1.2_3.0_1694776548569.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_geolearner","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_geolearner", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_geolearner| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/geolearner/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_gg1313_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_gg1313_en.md new file mode 100644 index 00000000000000..c2c14b7105869c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_gg1313_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_gg1313 DistilBertEmbeddings from Gg1313 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_gg1313 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_gg1313` is a English model originally trained by Gg1313. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_gg1313_en_5.1.2_3.0_1694791141518.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_gg1313_en_5.1.2_3.0_1694791141518.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_gg1313","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_gg1313", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_gg1313| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Gg1313/distilbert-base-uncased-finetuned_imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_golightly_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_golightly_en.md new file mode 100644 index 00000000000000..c5be2b207d61bb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_golightly_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_golightly DistilBertEmbeddings from golightly +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_golightly +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_golightly` is a English model originally trained by golightly. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_golightly_en_5.1.2_3.0_1694790800704.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_golightly_en_5.1.2_3.0_1694790800704.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_golightly","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_golightly", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_golightly| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/golightly/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_gtxygyzb_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_gtxygyzb_en.md new file mode 100644 index 00000000000000..74657841cfd68e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_gtxygyzb_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_gtxygyzb DistilBertEmbeddings from gtxygyzb +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_gtxygyzb +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_gtxygyzb` is a English model originally trained by gtxygyzb. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_gtxygyzb_en_5.1.2_3.0_1694783633507.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_gtxygyzb_en_5.1.2_3.0_1694783633507.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_gtxygyzb","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_gtxygyzb", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_gtxygyzb| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/gtxygyzb/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_guidoivetta_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_guidoivetta_en.md new file mode 100644 index 00000000000000..f5f7a5157b5230 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_guidoivetta_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_guidoivetta DistilBertEmbeddings from guidoivetta +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_guidoivetta +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_guidoivetta` is a English model originally trained by guidoivetta. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_guidoivetta_en_5.1.2_3.0_1694788838001.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_guidoivetta_en_5.1.2_3.0_1694788838001.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_guidoivetta","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_guidoivetta", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_guidoivetta| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/guidoivetta/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_harangus_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_harangus_en.md new file mode 100644 index 00000000000000..439cdf3b1dbe0c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_harangus_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_harangus DistilBertEmbeddings from Harangus +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_harangus +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_harangus` is a English model originally trained by Harangus. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_harangus_en_5.1.2_3.0_1694790359797.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_harangus_en_5.1.2_3.0_1694790359797.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_harangus","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_harangus", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_harangus| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Harangus/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_harshseth_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_harshseth_en.md new file mode 100644 index 00000000000000..80bee2d129ddce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_harshseth_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_harshseth DistilBertEmbeddings from harshseth +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_harshseth +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_harshseth` is a English model originally trained by harshseth. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_harshseth_en_5.1.2_3.0_1694789500099.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_harshseth_en_5.1.2_3.0_1694789500099.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_harshseth","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_harshseth", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_harshseth| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/harshseth/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_hemanth11_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_hemanth11_en.md new file mode 100644 index 00000000000000..665fcbc5416e32 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_hemanth11_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_hemanth11 DistilBertEmbeddings from hemanth11 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_hemanth11 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_hemanth11` is a English model originally trained by hemanth11. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_hemanth11_en_5.1.2_3.0_1694791749406.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_hemanth11_en_5.1.2_3.0_1694791749406.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_hemanth11","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_hemanth11", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_hemanth11| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/hemanth11/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_holtbui_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_holtbui_en.md new file mode 100644 index 00000000000000..47096c27f24d02 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_holtbui_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_holtbui DistilBertEmbeddings from holtbui +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_holtbui +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_holtbui` is a English model originally trained by holtbui. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_holtbui_en_5.1.2_3.0_1694787990455.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_holtbui_en_5.1.2_3.0_1694787990455.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_holtbui","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_holtbui", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_holtbui| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/holtbui/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_huggingface_course_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_huggingface_course_en.md new file mode 100644 index 00000000000000..893e4babd3a088 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_huggingface_course_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_huggingface_course DistilBertEmbeddings from huggingface-course +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_huggingface_course +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_huggingface_course` is a English model originally trained by huggingface-course. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_huggingface_course_en_5.1.2_3.0_1694780655866.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_huggingface_course_en_5.1.2_3.0_1694780655866.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_huggingface_course","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_huggingface_course", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_huggingface_course| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/huggingface-course/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_hxshen_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_hxshen_en.md new file mode 100644 index 00000000000000..aa74c5c6ede594 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_hxshen_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_hxshen DistilBertEmbeddings from hxshen +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_hxshen +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_hxshen` is a English model originally trained by hxshen. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_hxshen_en_5.1.2_3.0_1694788924518.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_hxshen_en_5.1.2_3.0_1694788924518.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_hxshen","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_hxshen", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_hxshen| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/hxshen/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_imxxn_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_imxxn_en.md new file mode 100644 index 00000000000000..7e47a9ed008b02 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_imxxn_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_imxxn DistilBertEmbeddings from Imxxn +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_imxxn +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_imxxn` is a English model originally trained by Imxxn. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_imxxn_en_5.1.2_3.0_1694777338856.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_imxxn_en_5.1.2_3.0_1694777338856.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_imxxn","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_imxxn", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_imxxn| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Imxxn/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_insub_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_insub_en.md new file mode 100644 index 00000000000000..fde7962a8d9c00 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_insub_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_insub DistilBertEmbeddings from insub +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_insub +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_insub` is a English model originally trained by insub. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_insub_en_5.1.2_3.0_1694772369747.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_insub_en_5.1.2_3.0_1694772369747.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_insub","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_insub", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_insub| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/insub/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_iotengtr_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_iotengtr_en.md new file mode 100644 index 00000000000000..b946a0f32dfe1b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_iotengtr_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_iotengtr DistilBertEmbeddings from iotengtr +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_iotengtr +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_iotengtr` is a English model originally trained by iotengtr. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_iotengtr_en_5.1.2_3.0_1694773541551.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_iotengtr_en_5.1.2_3.0_1694773541551.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_iotengtr","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_iotengtr", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_iotengtr| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/iotengtr/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_iven5880_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_iven5880_en.md new file mode 100644 index 00000000000000..ce21c11521f919 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_iven5880_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_iven5880 DistilBertEmbeddings from iven5880 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_iven5880 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_iven5880` is a English model originally trained by iven5880. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_iven5880_en_5.1.2_3.0_1694791025301.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_iven5880_en_5.1.2_3.0_1694791025301.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_iven5880","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_iven5880", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_iven5880| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/iven5880/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jaese_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jaese_en.md new file mode 100644 index 00000000000000..ab1c8c738d5acf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jaese_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_jaese DistilBertEmbeddings from jaese +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_jaese +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_jaese` is a English model originally trained by jaese. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jaese_en_5.1.2_3.0_1694791022657.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jaese_en_5.1.2_3.0_1694791022657.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_jaese","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_jaese", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_jaese| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jaese/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jake777_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jake777_en.md new file mode 100644 index 00000000000000..f1ea6bca6c5b72 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jake777_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_jake777 DistilBertEmbeddings from JAKE777 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_jake777 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_jake777` is a English model originally trained by JAKE777. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jake777_en_5.1.2_3.0_1694777853032.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jake777_en_5.1.2_3.0_1694777853032.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_jake777","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_jake777", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_jake777| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/JAKE777/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jchhabra_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jchhabra_en.md new file mode 100644 index 00000000000000..dbd8ea6e5bc839 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jchhabra_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_jchhabra DistilBertEmbeddings from jchhabra +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_jchhabra +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_jchhabra` is a English model originally trained by jchhabra. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jchhabra_en_5.1.2_3.0_1694788774737.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jchhabra_en_5.1.2_3.0_1694788774737.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_jchhabra","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_jchhabra", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_jchhabra| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jchhabra/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jjinbbangman_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jjinbbangman_en.md new file mode 100644 index 00000000000000..c3b178dfca6292 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jjinbbangman_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_jjinbbangman DistilBertEmbeddings from JJinBBangMan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_jjinbbangman +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_jjinbbangman` is a English model originally trained by JJinBBangMan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jjinbbangman_en_5.1.2_3.0_1694787034924.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jjinbbangman_en_5.1.2_3.0_1694787034924.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_jjinbbangman","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_jjinbbangman", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_jjinbbangman| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/JJinBBangMan/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_johnyyhk_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_johnyyhk_en.md new file mode 100644 index 00000000000000..4d0c68de8b954c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_johnyyhk_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_johnyyhk DistilBertEmbeddings from johnyyhk +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_johnyyhk +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_johnyyhk` is a English model originally trained by johnyyhk. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_johnyyhk_en_5.1.2_3.0_1694785221188.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_johnyyhk_en_5.1.2_3.0_1694785221188.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_johnyyhk","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_johnyyhk", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_johnyyhk| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/johnyyhk/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_junchengding_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_junchengding_en.md new file mode 100644 index 00000000000000..1d08533d2c1d00 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_junchengding_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_junchengding DistilBertEmbeddings from JunchengDing +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_junchengding +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_junchengding` is a English model originally trained by JunchengDing. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_junchengding_en_5.1.2_3.0_1694780502980.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_junchengding_en_5.1.2_3.0_1694780502980.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_junchengding","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_junchengding", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_junchengding| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/JunchengDing/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jwchung_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jwchung_en.md new file mode 100644 index 00000000000000..94047821a62227 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_jwchung_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_jwchung DistilBertEmbeddings from jwchung +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_jwchung +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_jwchung` is a English model originally trained by jwchung. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jwchung_en_5.1.2_3.0_1694774375800.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_jwchung_en_5.1.2_3.0_1694774375800.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_jwchung","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_jwchung", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_jwchung| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jwchung/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kar1sumax_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kar1sumax_en.md new file mode 100644 index 00000000000000..0f0af95c4077d2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kar1sumax_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_kar1sumax DistilBertEmbeddings from Kar1suMAX +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_kar1sumax +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_kar1sumax` is a English model originally trained by Kar1suMAX. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_kar1sumax_en_5.1.2_3.0_1694771169950.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_kar1sumax_en_5.1.2_3.0_1694771169950.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_kar1sumax","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_kar1sumax", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_kar1sumax| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Kar1suMAX/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kosec39_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kosec39_en.md new file mode 100644 index 00000000000000..8aa415a32b6c90 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kosec39_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_kosec39 DistilBertEmbeddings from kosec39 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_kosec39 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_kosec39` is a English model originally trained by kosec39. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_kosec39_en_5.1.2_3.0_1694771918349.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_kosec39_en_5.1.2_3.0_1694771918349.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_kosec39","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_kosec39", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_kosec39| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/kosec39/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ksaml_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ksaml_en.md new file mode 100644 index 00000000000000..85a16d6a391374 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ksaml_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_ksaml DistilBertEmbeddings from ksaml +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_ksaml +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_ksaml` is a English model originally trained by ksaml. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_ksaml_en_5.1.2_3.0_1694772454474.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_ksaml_en_5.1.2_3.0_1694772454474.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_ksaml","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_ksaml", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_ksaml| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ksaml/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kyle2023_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kyle2023_en.md new file mode 100644 index 00000000000000..e617536c967736 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_kyle2023_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_kyle2023 DistilBertEmbeddings from kyle2023 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_kyle2023 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_kyle2023` is a English model originally trained by kyle2023. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_kyle2023_en_5.1.2_3.0_1694788760520.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_kyle2023_en_5.1.2_3.0_1694788760520.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_kyle2023","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_kyle2023", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_kyle2023| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/kyle2023/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lindarz_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lindarz_en.md new file mode 100644 index 00000000000000..1316363d009c86 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lindarz_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_lindarz DistilBertEmbeddings from lindarz +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_lindarz +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_lindarz` is a English model originally trained by lindarz. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_lindarz_en_5.1.2_3.0_1694771058189.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_lindarz_en_5.1.2_3.0_1694771058189.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_lindarz","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_lindarz", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_lindarz| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/lindarz/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_liquannan_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_liquannan_en.md index 497cf8cf207580..1e789097ea533d 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_liquannan_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_liquannan_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_liquannan_en_5.1.2_3.0_1694736911779.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_liquannan_en_5.1.2_3.0_1694736911779.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_liquannan_en_5.1.2_3.0_1694770219474.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_liquannan_en_5.1.2_3.0_1694770219474.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lokeshsoni2801_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lokeshsoni2801_en.md new file mode 100644 index 00000000000000..51233de9251ce7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lokeshsoni2801_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_lokeshsoni2801 DistilBertEmbeddings from Lokeshsoni2801 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_lokeshsoni2801 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_lokeshsoni2801` is a English model originally trained by Lokeshsoni2801. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_lokeshsoni2801_en_5.1.2_3.0_1694770947224.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_lokeshsoni2801_en_5.1.2_3.0_1694770947224.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_lokeshsoni2801","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_lokeshsoni2801", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_lokeshsoni2801| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Lokeshsoni2801/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lsimon_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lsimon_en.md new file mode 100644 index 00000000000000..066072d4e9bdae --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_lsimon_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_lsimon DistilBertEmbeddings from lsimon +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_lsimon +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_lsimon` is a English model originally trained by lsimon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_lsimon_en_5.1.2_3.0_1694783337770.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_lsimon_en_5.1.2_3.0_1694783337770.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_lsimon","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_lsimon", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_lsimon| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/lsimon/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_luzimu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_luzimu_en.md new file mode 100644 index 00000000000000..2432be0cfaa61e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_luzimu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_luzimu DistilBertEmbeddings from luzimu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_luzimu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_luzimu` is a English model originally trained by luzimu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_luzimu_en_5.1.2_3.0_1694782954592.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_luzimu_en_5.1.2_3.0_1694782954592.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_luzimu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_luzimu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_luzimu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/luzimu/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_magnustragardh_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_magnustragardh_en.md new file mode 100644 index 00000000000000..59d521aa257ae9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_magnustragardh_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_magnustragardh DistilBertEmbeddings from magnustragardh +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_magnustragardh +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_magnustragardh` is a English model originally trained by magnustragardh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_magnustragardh_en_5.1.2_3.0_1694784349082.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_magnustragardh_en_5.1.2_3.0_1694784349082.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_magnustragardh","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_magnustragardh", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_magnustragardh| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/magnustragardh/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_manishw_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_manishw_en.md new file mode 100644 index 00000000000000..7adeccce72cddf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_manishw_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_manishw DistilBertEmbeddings from ManishW +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_manishw +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_manishw` is a English model originally trained by ManishW. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_manishw_en_5.1.2_3.0_1694779007105.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_manishw_en_5.1.2_3.0_1694779007105.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_manishw","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_manishw", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_manishw| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ManishW/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_marccram_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_marccram_en.md new file mode 100644 index 00000000000000..359af8942ad663 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_marccram_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_marccram DistilBertEmbeddings from marccram +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_marccram +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_marccram` is a English model originally trained by marccram. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_marccram_en_5.1.2_3.0_1694771311229.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_marccram_en_5.1.2_3.0_1694771311229.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_marccram","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_marccram", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_marccram| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/marccram/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_martingui_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_martingui_en.md new file mode 100644 index 00000000000000..17cc99ea75ac7b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_martingui_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_martingui DistilBertEmbeddings from MartinGui +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_martingui +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_martingui` is a English model originally trained by MartinGui. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_martingui_en_5.1.2_3.0_1694786646812.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_martingui_en_5.1.2_3.0_1694786646812.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_martingui","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_martingui", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_martingui| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/MartinGui/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mattiaparavisi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mattiaparavisi_en.md new file mode 100644 index 00000000000000..738ad55426e54b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mattiaparavisi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_mattiaparavisi DistilBertEmbeddings from MattiaParavisi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_mattiaparavisi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_mattiaparavisi` is a English model originally trained by MattiaParavisi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mattiaparavisi_en_5.1.2_3.0_1694782470244.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mattiaparavisi_en_5.1.2_3.0_1694782470244.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_mattiaparavisi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_mattiaparavisi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_mattiaparavisi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/MattiaParavisi/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_maysamalfiza_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_maysamalfiza_en.md new file mode 100644 index 00000000000000..133c958c38779c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_maysamalfiza_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_maysamalfiza DistilBertEmbeddings from maysamalfiza +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_maysamalfiza +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_maysamalfiza` is a English model originally trained by maysamalfiza. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_maysamalfiza_en_5.1.2_3.0_1694789818242.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_maysamalfiza_en_5.1.2_3.0_1694789818242.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_maysamalfiza","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_maysamalfiza", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_maysamalfiza| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/maysamalfiza/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mchalek_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mchalek_en.md new file mode 100644 index 00000000000000..6cd24d86760a96 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mchalek_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_mchalek DistilBertEmbeddings from mchalek +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_mchalek +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_mchalek` is a English model originally trained by mchalek. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mchalek_en_5.1.2_3.0_1694790810503.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mchalek_en_5.1.2_3.0_1694790810503.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_mchalek","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_mchalek", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_mchalek| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mchalek/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mholi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mholi_en.md new file mode 100644 index 00000000000000..0a48e83d439f16 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mholi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_mholi DistilBertEmbeddings from mholi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_mholi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_mholi` is a English model originally trained by mholi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mholi_en_5.1.2_3.0_1694774114982.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mholi_en_5.1.2_3.0_1694774114982.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_mholi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_mholi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_mholi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mholi/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mildmillard_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mildmillard_en.md new file mode 100644 index 00000000000000..8053e8d6830bb3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mildmillard_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_mildmillard DistilBertEmbeddings from mildmillard +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_mildmillard +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_mildmillard` is a English model originally trained by mildmillard. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mildmillard_en_5.1.2_3.0_1694788468751.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mildmillard_en_5.1.2_3.0_1694788468751.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_mildmillard","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_mildmillard", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_mildmillard| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mildmillard/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mintz1104_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mintz1104_en.md new file mode 100644 index 00000000000000..ce1a8e679e3743 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mintz1104_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_mintz1104 DistilBertEmbeddings from mintz1104 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_mintz1104 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_mintz1104` is a English model originally trained by mintz1104. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mintz1104_en_5.1.2_3.0_1694783458456.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mintz1104_en_5.1.2_3.0_1694783458456.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_mintz1104","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_mintz1104", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_mintz1104| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mintz1104/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_minye819_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_minye819_en.md new file mode 100644 index 00000000000000..981398a5275064 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_minye819_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_minye819 DistilBertEmbeddings from minye819 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_minye819 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_minye819` is a English model originally trained by minye819. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_minye819_en_5.1.2_3.0_1694785732543.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_minye819_en_5.1.2_3.0_1694785732543.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_minye819","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_minye819", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_minye819| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/minye819/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mlm_accelerate_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mlm_accelerate_en.md new file mode 100644 index 00000000000000..0e9588d860230f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mlm_accelerate_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_mlm_accelerate DistilBertEmbeddings from pritam3355 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_mlm_accelerate +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_mlm_accelerate` is a English model originally trained by pritam3355. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mlm_accelerate_en_5.1.2_3.0_1694783358290.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mlm_accelerate_en_5.1.2_3.0_1694783358290.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_mlm_accelerate","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_mlm_accelerate", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_mlm_accelerate| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/pritam3355/distilbert-base-uncased-finetuned-imdb-mlm-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mulinski_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mulinski_en.md new file mode 100644 index 00000000000000..a9a4057f89695c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mulinski_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_mulinski DistilBertEmbeddings from mulinski +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_mulinski +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_mulinski` is a English model originally trained by mulinski. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mulinski_en_5.1.2_3.0_1694776177033.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mulinski_en_5.1.2_3.0_1694776177033.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_mulinski","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_mulinski", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_mulinski| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mulinski/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mxalmeida_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mxalmeida_en.md new file mode 100644 index 00000000000000..41c4c1bbd6112e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_mxalmeida_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_mxalmeida DistilBertEmbeddings from mxalmeida +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_mxalmeida +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_mxalmeida` is a English model originally trained by mxalmeida. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mxalmeida_en_5.1.2_3.0_1694783674388.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_mxalmeida_en_5.1.2_3.0_1694783674388.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_mxalmeida","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_mxalmeida", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_mxalmeida| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mxalmeida/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_nugget00_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_nugget00_en.md new file mode 100644 index 00000000000000..4409f03c189a88 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_nugget00_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_nugget00 DistilBertEmbeddings from nugget00 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_nugget00 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_nugget00` is a English model originally trained by nugget00. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_nugget00_en_5.1.2_3.0_1694788096126.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_nugget00_en_5.1.2_3.0_1694788096126.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_nugget00","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_nugget00", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_nugget00| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/nugget00/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_orangelu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_orangelu_en.md new file mode 100644 index 00000000000000..97c078a6e5b710 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_orangelu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_orangelu DistilBertEmbeddings from orangelu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_orangelu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_orangelu` is a English model originally trained by orangelu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_orangelu_en_5.1.2_3.0_1694786367577.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_orangelu_en_5.1.2_3.0_1694786367577.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_orangelu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_orangelu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_orangelu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/orangelu/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_parchiev_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_parchiev_en.md new file mode 100644 index 00000000000000..7341b84fd633a3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_parchiev_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_parchiev DistilBertEmbeddings from parchiev +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_parchiev +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_parchiev` is a English model originally trained by parchiev. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_parchiev_en_5.1.2_3.0_1694771616239.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_parchiev_en_5.1.2_3.0_1694771616239.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_parchiev","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_parchiev", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_parchiev| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/parchiev/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_pattom_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_pattom_en.md new file mode 100644 index 00000000000000..9fb28b2b1fab35 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_pattom_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_pattom DistilBertEmbeddings from pattom +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_pattom +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_pattom` is a English model originally trained by pattom. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_pattom_en_5.1.2_3.0_1694785696930.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_pattom_en_5.1.2_3.0_1694785696930.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_pattom","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_pattom", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_pattom| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/pattom/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_peterhsu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_peterhsu_en.md new file mode 100644 index 00000000000000..b71c0181d15293 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_peterhsu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_peterhsu DistilBertEmbeddings from peterhsu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_peterhsu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_peterhsu` is a English model originally trained by peterhsu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_peterhsu_en_5.1.2_3.0_1694783528508.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_peterhsu_en_5.1.2_3.0_1694783528508.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_peterhsu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_peterhsu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_peterhsu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/peterhsu/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_peteryushunli_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_peteryushunli_en.md new file mode 100644 index 00000000000000..237e7a73f09e5e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_peteryushunli_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_peteryushunli DistilBertEmbeddings from peteryushunli +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_peteryushunli +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_peteryushunli` is a English model originally trained by peteryushunli. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_peteryushunli_en_5.1.2_3.0_1694784593034.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_peteryushunli_en_5.1.2_3.0_1694784593034.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_peteryushunli","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_peteryushunli", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_peteryushunli| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/peteryushunli/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_physhunter_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_physhunter_en.md new file mode 100644 index 00000000000000..41adc211b1df3f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_physhunter_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_physhunter DistilBertEmbeddings from PhysHunter +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_physhunter +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_physhunter` is a English model originally trained by PhysHunter. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_physhunter_en_5.1.2_3.0_1694772969529.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_physhunter_en_5.1.2_3.0_1694772969529.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_physhunter","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_physhunter", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_physhunter| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/PhysHunter/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_pierre_arthur_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_pierre_arthur_en.md new file mode 100644 index 00000000000000..7654d1053146fd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_pierre_arthur_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_pierre_arthur DistilBertEmbeddings from Pierre-Arthur +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_pierre_arthur +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_pierre_arthur` is a English model originally trained by Pierre-Arthur. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_pierre_arthur_en_5.1.2_3.0_1694778085444.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_pierre_arthur_en_5.1.2_3.0_1694778085444.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_pierre_arthur","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_pierre_arthur", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_pierre_arthur| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Pierre-Arthur/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_poplkl_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_poplkl_en.md new file mode 100644 index 00000000000000..ac1d92179e7b0f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_poplkl_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_poplkl DistilBertEmbeddings from poplkl +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_poplkl +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_poplkl` is a English model originally trained by poplkl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_poplkl_en_5.1.2_3.0_1694778090892.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_poplkl_en_5.1.2_3.0_1694778090892.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_poplkl","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_poplkl", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_poplkl| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/poplkl/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_prasanthin_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_prasanthin_en.md new file mode 100644 index 00000000000000..6884d0f95bdbcc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_prasanthin_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_prasanthin DistilBertEmbeddings from Prasanthin +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_prasanthin +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_prasanthin` is a English model originally trained by Prasanthin. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_prasanthin_en_5.1.2_3.0_1694791836770.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_prasanthin_en_5.1.2_3.0_1694791836770.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_prasanthin","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_prasanthin", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_prasanthin| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Prasanthin/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_qianyu88_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_qianyu88_en.md new file mode 100644 index 00000000000000..bd4fc552267259 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_qianyu88_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_qianyu88 DistilBertEmbeddings from qianyu88 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_qianyu88 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_qianyu88` is a English model originally trained by qianyu88. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_qianyu88_en_5.1.2_3.0_1694791401990.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_qianyu88_en_5.1.2_3.0_1694791401990.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_qianyu88","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_qianyu88", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_qianyu88| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/qianyu88/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rajknakka_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rajknakka_en.md new file mode 100644 index 00000000000000..1ba868fc50d4b4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rajknakka_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_rajknakka DistilBertEmbeddings from RajkNakka +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_rajknakka +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_rajknakka` is a English model originally trained by RajkNakka. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rajknakka_en_5.1.2_3.0_1694789607833.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rajknakka_en_5.1.2_3.0_1694789607833.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_rajknakka","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_rajknakka", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_rajknakka| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/RajkNakka/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_raphaelmerx_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_raphaelmerx_en.md new file mode 100644 index 00000000000000..7d8ba517a2bac4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_raphaelmerx_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_raphaelmerx DistilBertEmbeddings from raphaelmerx +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_raphaelmerx +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_raphaelmerx` is a English model originally trained by raphaelmerx. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_raphaelmerx_en_5.1.2_3.0_1694783693258.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_raphaelmerx_en_5.1.2_3.0_1694783693258.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_raphaelmerx","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_raphaelmerx", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_raphaelmerx| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/raphaelmerx/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_raulgdp_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_raulgdp_en.md new file mode 100644 index 00000000000000..78b12fc538a71a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_raulgdp_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_raulgdp DistilBertEmbeddings from raulgdp +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_raulgdp +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_raulgdp` is a English model originally trained by raulgdp. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_raulgdp_en_5.1.2_3.0_1694777650610.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_raulgdp_en_5.1.2_3.0_1694777650610.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_raulgdp","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_raulgdp", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_raulgdp| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/raulgdp/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ray2791_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ray2791_en.md new file mode 100644 index 00000000000000..501b64bc880b82 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ray2791_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_ray2791 DistilBertEmbeddings from Ray2791 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_ray2791 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_ray2791` is a English model originally trained by Ray2791. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_ray2791_en_5.1.2_3.0_1694777725820.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_ray2791_en_5.1.2_3.0_1694777725820.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_ray2791","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_ray2791", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_ray2791| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Ray2791/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rayguo2023_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rayguo2023_en.md new file mode 100644 index 00000000000000..73aa24abb3ba54 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rayguo2023_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_rayguo2023 DistilBertEmbeddings from RayGuo2023 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_rayguo2023 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_rayguo2023` is a English model originally trained by RayGuo2023. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rayguo2023_en_5.1.2_3.0_1694778200046.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rayguo2023_en_5.1.2_3.0_1694778200046.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_rayguo2023","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_rayguo2023", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_rayguo2023| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/RayGuo2023/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rd124_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rd124_en.md new file mode 100644 index 00000000000000..84a7e06d499854 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rd124_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_rd124 DistilBertEmbeddings from rd124 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_rd124 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_rd124` is a English model originally trained by rd124. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rd124_en_5.1.2_3.0_1694790386344.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rd124_en_5.1.2_3.0_1694790386344.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_rd124","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_rd124", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_rd124| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/rd124/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rdvdsn_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rdvdsn_en.md new file mode 100644 index 00000000000000..5708a4f1a88796 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rdvdsn_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_rdvdsn DistilBertEmbeddings from rdvdsn +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_rdvdsn +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_rdvdsn` is a English model originally trained by rdvdsn. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rdvdsn_en_5.1.2_3.0_1694786547240.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rdvdsn_en_5.1.2_3.0_1694786547240.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_rdvdsn","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_rdvdsn", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_rdvdsn| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/rdvdsn/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_renyulin_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_renyulin_en.md new file mode 100644 index 00000000000000..61b80ff542bdc8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_renyulin_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_renyulin DistilBertEmbeddings from renyulin +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_renyulin +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_renyulin` is a English model originally trained by renyulin. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_renyulin_en_5.1.2_3.0_1694773717620.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_renyulin_en_5.1.2_3.0_1694773717620.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_renyulin","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_renyulin", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_renyulin| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/renyulin/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_replicate_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_replicate_en.md new file mode 100644 index 00000000000000..423b4eb65b7753 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_replicate_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_replicate DistilBertEmbeddings from hxshen +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_replicate +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_replicate` is a English model originally trained by hxshen. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_replicate_en_5.1.2_3.0_1694790283986.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_replicate_en_5.1.2_3.0_1694790283986.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_replicate","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_replicate", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_replicate| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/hxshen/distilbert-base-uncased-finetuned-imdb-replicate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_reza93v_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_reza93v_en.md new file mode 100644 index 00000000000000..1f4f6a5d579498 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_reza93v_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_reza93v DistilBertEmbeddings from reza93v +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_reza93v +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_reza93v` is a English model originally trained by reza93v. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_reza93v_en_5.1.2_3.0_1694791487598.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_reza93v_en_5.1.2_3.0_1694791487598.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_reza93v","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_reza93v", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_reza93v| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/reza93v/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_robkayinto_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_robkayinto_en.md new file mode 100644 index 00000000000000..bc850f49e0ee85 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_robkayinto_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_robkayinto DistilBertEmbeddings from robkayinto +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_robkayinto +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_robkayinto` is a English model originally trained by robkayinto. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_robkayinto_en_5.1.2_3.0_1694771947206.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_robkayinto_en_5.1.2_3.0_1694771947206.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_robkayinto","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_robkayinto", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_robkayinto| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/robkayinto/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rugo_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rugo_en.md new file mode 100644 index 00000000000000..23f2a3e442b287 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_rugo_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_rugo DistilBertEmbeddings from rugo +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_rugo +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_rugo` is a English model originally trained by rugo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rugo_en_5.1.2_3.0_1694783203222.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_rugo_en_5.1.2_3.0_1694783203222.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_rugo","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_rugo", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_rugo| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/rugo/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ryanlai_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ryanlai_en.md new file mode 100644 index 00000000000000..867411875662ac --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_ryanlai_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_ryanlai DistilBertEmbeddings from ryanlai +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_ryanlai +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_ryanlai` is a English model originally trained by ryanlai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_ryanlai_en_5.1.2_3.0_1694786984703.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_ryanlai_en_5.1.2_3.0_1694786984703.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_ryanlai","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_ryanlai", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_ryanlai| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ryanlai/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sabby_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sabby_en.md index 155b5987b5e13d..9ab0de2344b2ec 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sabby_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sabby_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sabby_en_5.1.2_3.0_1694736793793.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sabby_en_5.1.2_3.0_1694736793793.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sabby_en_5.1.2_3.0_1694770099489.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sabby_en_5.1.2_3.0_1694770099489.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sakaijun_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sakaijun_en.md new file mode 100644 index 00000000000000..878991606f333c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sakaijun_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_sakaijun DistilBertEmbeddings from SakaiJun +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_sakaijun +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_sakaijun` is a English model originally trained by SakaiJun. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sakaijun_en_5.1.2_3.0_1694771049150.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sakaijun_en_5.1.2_3.0_1694771049150.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_sakaijun","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_sakaijun", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_sakaijun| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/SakaiJun/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_san94_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_san94_en.md new file mode 100644 index 00000000000000..d11174761785b4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_san94_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_san94 DistilBertEmbeddings from san94 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_san94 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_san94` is a English model originally trained by san94. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_san94_en_5.1.2_3.0_1694771416174.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_san94_en_5.1.2_3.0_1694771416174.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_san94","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_san94", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_san94| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/san94/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sarmila_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sarmila_en.md new file mode 100644 index 00000000000000..78661557f06760 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sarmila_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_sarmila DistilBertEmbeddings from Sarmila +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_sarmila +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_sarmila` is a English model originally trained by Sarmila. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sarmila_en_5.1.2_3.0_1694776735479.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sarmila_en_5.1.2_3.0_1694776735479.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_sarmila","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_sarmila", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_sarmila| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Sarmila/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sarthakc44_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sarthakc44_en.md new file mode 100644 index 00000000000000..12aa256cd8feb0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sarthakc44_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_sarthakc44 DistilBertEmbeddings from sarthakc44 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_sarthakc44 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_sarthakc44` is a English model originally trained by sarthakc44. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sarthakc44_en_5.1.2_3.0_1694773301034.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sarthakc44_en_5.1.2_3.0_1694773301034.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_sarthakc44","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_sarthakc44", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_sarthakc44| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/sarthakc44/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_satyashetty_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_satyashetty_en.md new file mode 100644 index 00000000000000..1ed1a185d38997 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_satyashetty_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_satyashetty DistilBertEmbeddings from satyashetty +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_satyashetty +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_satyashetty` is a English model originally trained by satyashetty. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_satyashetty_en_5.1.2_3.0_1694781764485.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_satyashetty_en_5.1.2_3.0_1694781764485.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_satyashetty","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_satyashetty", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_satyashetty| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/satyashetty/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sertemo_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sertemo_en.md new file mode 100644 index 00000000000000..d0970c40da7edd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sertemo_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_sertemo DistilBertEmbeddings from sertemo +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_sertemo +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_sertemo` is a English model originally trained by sertemo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sertemo_en_5.1.2_3.0_1694770457266.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sertemo_en_5.1.2_3.0_1694770457266.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_sertemo","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_sertemo", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_sertemo| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/sertemo/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sgasparorippa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sgasparorippa_en.md new file mode 100644 index 00000000000000..2ecb6be829de77 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sgasparorippa_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_sgasparorippa DistilBertEmbeddings from sgasparorippa +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_sgasparorippa +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_sgasparorippa` is a English model originally trained by sgasparorippa. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sgasparorippa_en_5.1.2_3.0_1694776057551.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sgasparorippa_en_5.1.2_3.0_1694776057551.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_sgasparorippa","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_sgasparorippa", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_sgasparorippa| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/sgasparorippa/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shahriarebrampour_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shahriarebrampour_en.md new file mode 100644 index 00000000000000..3e3884debc4b28 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shahriarebrampour_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_shahriarebrampour DistilBertEmbeddings from shahriarebrampour +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_shahriarebrampour +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_shahriarebrampour` is a English model originally trained by shahriarebrampour. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_shahriarebrampour_en_5.1.2_3.0_1694788371168.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_shahriarebrampour_en_5.1.2_3.0_1694788371168.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_shahriarebrampour","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_shahriarebrampour", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_shahriarebrampour| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/shahriarebrampour/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shre_db_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shre_db_en.md new file mode 100644 index 00000000000000..10467160eef45a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shre_db_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_shre_db DistilBertEmbeddings from shre-db +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_shre_db +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_shre_db` is a English model originally trained by shre-db. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_shre_db_en_5.1.2_3.0_1694782000633.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_shre_db_en_5.1.2_3.0_1694782000633.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_shre_db","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_shre_db", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_shre_db| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/shre-db/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shreyasdatar_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shreyasdatar_en.md new file mode 100644 index 00000000000000..9460dd524f637f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_shreyasdatar_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_shreyasdatar DistilBertEmbeddings from shreyasdatar +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_shreyasdatar +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_shreyasdatar` is a English model originally trained by shreyasdatar. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_shreyasdatar_en_5.1.2_3.0_1694776445411.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_shreyasdatar_en_5.1.2_3.0_1694776445411.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_shreyasdatar","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_shreyasdatar", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_shreyasdatar| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/shreyasdatar/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_smarquie_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_smarquie_en.md new file mode 100644 index 00000000000000..ed761d1542d162 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_smarquie_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_smarquie DistilBertEmbeddings from smarquie +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_smarquie +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_smarquie` is a English model originally trained by smarquie. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_smarquie_en_5.1.2_3.0_1694779920112.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_smarquie_en_5.1.2_3.0_1694779920112.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_smarquie","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_smarquie", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_smarquie| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/smarquie/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_snousias_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_snousias_en.md new file mode 100644 index 00000000000000..ecfa350dccffc4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_snousias_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_snousias DistilBertEmbeddings from snousias +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_snousias +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_snousias` is a English model originally trained by snousias. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_snousias_en_5.1.2_3.0_1694771960892.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_snousias_en_5.1.2_3.0_1694771960892.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_snousias","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_snousias", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_snousias| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/snousias/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sofa566_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sofa566_en.md new file mode 100644 index 00000000000000..02b2390b968550 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sofa566_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_sofa566 DistilBertEmbeddings from sofa566 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_sofa566 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_sofa566` is a English model originally trained by sofa566. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sofa566_en_5.1.2_3.0_1694780390044.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sofa566_en_5.1.2_3.0_1694780390044.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_sofa566","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_sofa566", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_sofa566| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/sofa566/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_solver_paul_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_solver_paul_en.md new file mode 100644 index 00000000000000..cd7424bfa94d9b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_solver_paul_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_solver_paul DistilBertEmbeddings from solver-paul +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_solver_paul +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_solver_paul` is a English model originally trained by solver-paul. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_solver_paul_en_5.1.2_3.0_1694781878267.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_solver_paul_en_5.1.2_3.0_1694781878267.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_solver_paul","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_solver_paul", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_solver_paul| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/solver-paul/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sonali_behera_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sonali_behera_en.md new file mode 100644 index 00000000000000..80d33229edbdb7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sonali_behera_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_sonali_behera DistilBertEmbeddings from Sonali-Behera +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_sonali_behera +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_sonali_behera` is a English model originally trained by Sonali-Behera. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sonali_behera_en_5.1.2_3.0_1694777089415.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sonali_behera_en_5.1.2_3.0_1694777089415.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_sonali_behera","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_sonali_behera", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_sonali_behera| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Sonali-Behera/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sumedha_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sumedha_en.md new file mode 100644 index 00000000000000..5dc9c50f7f2f47 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_sumedha_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_sumedha DistilBertEmbeddings from Sumedha +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_sumedha +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_sumedha` is a English model originally trained by Sumedha. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sumedha_en_5.1.2_3.0_1694772327267.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_sumedha_en_5.1.2_3.0_1694772327267.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_sumedha","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_sumedha", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_sumedha| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Sumedha/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_supersokol_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_supersokol_en.md new file mode 100644 index 00000000000000..91f40b986bcd2e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_supersokol_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_supersokol DistilBertEmbeddings from SUPERSOKOL +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_supersokol +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_supersokol` is a English model originally trained by SUPERSOKOL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_supersokol_en_5.1.2_3.0_1694785118271.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_supersokol_en_5.1.2_3.0_1694785118271.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_supersokol","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_supersokol", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_supersokol| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/SUPERSOKOL/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_surjray_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_surjray_en.md new file mode 100644 index 00000000000000..f642086c54e41c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_surjray_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_surjray DistilBertEmbeddings from surjray +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_surjray +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_surjray` is a English model originally trained by surjray. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_surjray_en_5.1.2_3.0_1694778304075.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_surjray_en_5.1.2_3.0_1694778304075.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_surjray","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_surjray", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_surjray| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/surjray/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_susghosh_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_susghosh_en.md new file mode 100644 index 00000000000000..7d408a50f8418e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_susghosh_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_susghosh DistilBertEmbeddings from susghosh +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_susghosh +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_susghosh` is a English model originally trained by susghosh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_susghosh_en_5.1.2_3.0_1694781874762.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_susghosh_en_5.1.2_3.0_1694781874762.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_susghosh","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_susghosh", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_susghosh| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/susghosh/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_talha185_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_talha185_en.md new file mode 100644 index 00000000000000..bc36425da7d080 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_talha185_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_talha185 DistilBertEmbeddings from Talha185 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_talha185 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_talha185` is a English model originally trained by Talha185. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_talha185_en_5.1.2_3.0_1694772261015.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_talha185_en_5.1.2_3.0_1694772261015.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_talha185","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_talha185", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_talha185| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Talha185/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_techtank_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_techtank_en.md new file mode 100644 index 00000000000000..cae38c16a10a9b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_techtank_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_techtank DistilBertEmbeddings from techtank +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_techtank +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_techtank` is a English model originally trained by techtank. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_techtank_en_5.1.2_3.0_1694785949232.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_techtank_en_5.1.2_3.0_1694785949232.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_techtank","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_techtank", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_techtank| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/techtank/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_terps_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_terps_en.md new file mode 100644 index 00000000000000..6e26c7c64c3dda --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_terps_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_terps DistilBertEmbeddings from Terps +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_terps +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_terps` is a English model originally trained by Terps. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_terps_en_5.1.2_3.0_1694790485061.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_terps_en_5.1.2_3.0_1694790485061.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_terps","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_terps", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_terps| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Terps/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thangvip_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thangvip_en.md new file mode 100644 index 00000000000000..ac1647a221a16f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thangvip_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_thangvip DistilBertEmbeddings from thangvip +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_thangvip +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_thangvip` is a English model originally trained by thangvip. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_thangvip_en_5.1.2_3.0_1694791230390.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_thangvip_en_5.1.2_3.0_1694791230390.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_thangvip","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_thangvip", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_thangvip| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/thangvip/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thaophung_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thaophung_en.md new file mode 100644 index 00000000000000..73c55c4da2c560 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thaophung_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_thaophung DistilBertEmbeddings from thaophung +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_thaophung +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_thaophung` is a English model originally trained by thaophung. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_thaophung_en_5.1.2_3.0_1694772963814.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_thaophung_en_5.1.2_3.0_1694772963814.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_thaophung","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_thaophung", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_thaophung| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/thaophung/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thetaphipsi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thetaphipsi_en.md new file mode 100644 index 00000000000000..54a2bea240c373 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thetaphipsi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_thetaphipsi DistilBertEmbeddings from ThetaPhiPsi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_thetaphipsi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_thetaphipsi` is a English model originally trained by ThetaPhiPsi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_thetaphipsi_en_5.1.2_3.0_1694781139251.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_thetaphipsi_en_5.1.2_3.0_1694781139251.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_thetaphipsi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_thetaphipsi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_thetaphipsi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ThetaPhiPsi/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_threite_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_threite_en.md new file mode 100644 index 00000000000000..7c340ddd3dd6b4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_threite_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_threite DistilBertEmbeddings from threite +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_threite +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_threite` is a English model originally trained by threite. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_threite_en_5.1.2_3.0_1694788185263.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_threite_en_5.1.2_3.0_1694788185263.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_threite","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_threite", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_threite| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/threite/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thutrang_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thutrang_en.md new file mode 100644 index 00000000000000..21b9dc45959db0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_thutrang_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_thutrang DistilBertEmbeddings from ThuTrang +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_thutrang +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_thutrang` is a English model originally trained by ThuTrang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_thutrang_en_5.1.2_3.0_1694789894015.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_thutrang_en_5.1.2_3.0_1694789894015.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_thutrang","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_thutrang", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_thutrang| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ThuTrang/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_timtl_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_timtl_en.md new file mode 100644 index 00000000000000..c35ee439580c6e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_timtl_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_timtl DistilBertEmbeddings from TimTL +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_timtl +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_timtl` is a English model originally trained by TimTL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_timtl_en_5.1.2_3.0_1694784349104.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_timtl_en_5.1.2_3.0_1694784349104.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_timtl","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_timtl", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_timtl| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/TimTL/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tkoyama_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tkoyama_en.md new file mode 100644 index 00000000000000..d45409b3924e4d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tkoyama_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_tkoyama DistilBertEmbeddings from tkoyama +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_tkoyama +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_tkoyama` is a English model originally trained by tkoyama. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tkoyama_en_5.1.2_3.0_1694788619647.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tkoyama_en_5.1.2_3.0_1694788619647.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_tkoyama","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_tkoyama", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_tkoyama| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/tkoyama/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tlapusan_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tlapusan_en.md new file mode 100644 index 00000000000000..e000090cfebd8a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tlapusan_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_tlapusan DistilBertEmbeddings from tlapusan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_tlapusan +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_tlapusan` is a English model originally trained by tlapusan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tlapusan_en_5.1.2_3.0_1694789306473.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tlapusan_en_5.1.2_3.0_1694789306473.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_tlapusan","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_tlapusan", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_tlapusan| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/tlapusan/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tofunumber1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tofunumber1_en.md new file mode 100644 index 00000000000000..352b638c92fb6f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tofunumber1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_tofunumber1 DistilBertEmbeddings from TofuNumber1 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_tofunumber1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_tofunumber1` is a English model originally trained by TofuNumber1. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tofunumber1_en_5.1.2_3.0_1694776635641.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tofunumber1_en_5.1.2_3.0_1694776635641.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_tofunumber1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_tofunumber1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_tofunumber1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/TofuNumber1/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tsahhi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tsahhi_en.md new file mode 100644 index 00000000000000..38674573a4d5a2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tsahhi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_tsahhi DistilBertEmbeddings from Tsahhi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_tsahhi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_tsahhi` is a English model originally trained by Tsahhi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tsahhi_en_5.1.2_3.0_1694788650908.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tsahhi_en_5.1.2_3.0_1694788650908.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_tsahhi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_tsahhi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_tsahhi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Tsahhi/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tux_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tux_en.md new file mode 100644 index 00000000000000..23da54dbc779d0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tux_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_tux DistilBertEmbeddings from tux +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_tux +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_tux` is a English model originally trained by tux. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tux_en_5.1.2_3.0_1694786698878.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tux_en_5.1.2_3.0_1694786698878.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_tux","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_tux", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_tux| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/tux/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tyson0420_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tyson0420_en.md new file mode 100644 index 00000000000000..cc0f26202bbe37 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_tyson0420_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_tyson0420 DistilBertEmbeddings from tyson0420 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_tyson0420 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_tyson0420` is a English model originally trained by tyson0420. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tyson0420_en_5.1.2_3.0_1694775228117.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_tyson0420_en_5.1.2_3.0_1694775228117.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_tyson0420","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_tyson0420", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_tyson0420| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/tyson0420/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_udoy_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_udoy_en.md new file mode 100644 index 00000000000000..e61ee669c6ab02 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_udoy_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_udoy DistilBertEmbeddings from Udoy +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_udoy +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_udoy` is a English model originally trained by Udoy. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_udoy_en_5.1.2_3.0_1694786003499.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_udoy_en_5.1.2_3.0_1694786003499.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_udoy","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_udoy", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_udoy| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Udoy/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_accelerate_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_accelerate_en.md new file mode 100644 index 00000000000000..af4706e8fbe3ee --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_accelerate_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_v2_accelerate DistilBertEmbeddings from kaiku03 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_v2_accelerate +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_v2_accelerate` is a English model originally trained by kaiku03. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_v2_accelerate_en_5.1.2_3.0_1694789614333.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_v2_accelerate_en_5.1.2_3.0_1694789614333.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_v2_accelerate","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_v2_accelerate", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_v2_accelerate| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/kaiku03/distilbert-base-uncased-finetuned-imdb_v2_accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_francesco_a_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_francesco_a_en.md new file mode 100644 index 00000000000000..21216c3d68f8ce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_francesco_a_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_v2_francesco_a DistilBertEmbeddings from Francesco-A +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_v2_francesco_a +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_v2_francesco_a` is a English model originally trained by Francesco-A. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_v2_francesco_a_en_5.1.2_3.0_1694783237772.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_v2_francesco_a_en_5.1.2_3.0_1694783237772.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_v2_francesco_a","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_v2_francesco_a", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_v2_francesco_a| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Francesco-A/distilbert-base-uncased-finetuned-imdb-v2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_rd124_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_rd124_en.md new file mode 100644 index 00000000000000..9bbe40429ed6ce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_v2_rd124_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_v2_rd124 DistilBertEmbeddings from rd124 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_v2_rd124 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_v2_rd124` is a English model originally trained by rd124. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_v2_rd124_en_5.1.2_3.0_1694790490326.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_v2_rd124_en_5.1.2_3.0_1694790490326.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_v2_rd124","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_v2_rd124", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_v2_rd124| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/rd124/distilbert-base-uncased-finetuned-imdb-v2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vanhoan_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vanhoan_en.md new file mode 100644 index 00000000000000..d0beec3e4579d7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vanhoan_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_vanhoan DistilBertEmbeddings from VanHoan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_vanhoan +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_vanhoan` is a English model originally trained by VanHoan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_vanhoan_en_5.1.2_3.0_1694783996380.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_vanhoan_en_5.1.2_3.0_1694783996380.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_vanhoan","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_vanhoan", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_vanhoan| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/VanHoan/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_venkyz9_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_venkyz9_en.md new file mode 100644 index 00000000000000..a18874b7686d58 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_venkyz9_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_venkyz9 DistilBertEmbeddings from venkyz9 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_venkyz9 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_venkyz9` is a English model originally trained by venkyz9. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_venkyz9_en_5.1.2_3.0_1694777457894.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_venkyz9_en_5.1.2_3.0_1694777457894.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_venkyz9","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_venkyz9", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_venkyz9| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/venkyz9/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vibharkchauhan_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vibharkchauhan_en.md new file mode 100644 index 00000000000000..5d10c910439a5f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vibharkchauhan_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_vibharkchauhan DistilBertEmbeddings from Vibharkchauhan +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_vibharkchauhan +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_vibharkchauhan` is a English model originally trained by Vibharkchauhan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_vibharkchauhan_en_5.1.2_3.0_1694770670699.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_vibharkchauhan_en_5.1.2_3.0_1694770670699.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_vibharkchauhan","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_vibharkchauhan", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_vibharkchauhan| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Vibharkchauhan/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vives_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vives_en.md new file mode 100644 index 00000000000000..0b575aff66f065 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vives_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_vives DistilBertEmbeddings from vives +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_vives +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_vives` is a English model originally trained by vives. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_vives_en_5.1.2_3.0_1694772503575.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_vives_en_5.1.2_3.0_1694772503575.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_vives","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_vives", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_vives| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/vives/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vsrinivas_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vsrinivas_en.md new file mode 100644 index 00000000000000..0429da59fdcdfa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_vsrinivas_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_vsrinivas DistilBertEmbeddings from vsrinivas +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_vsrinivas +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_vsrinivas` is a English model originally trained by vsrinivas. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_vsrinivas_en_5.1.2_3.0_1694787983867.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_vsrinivas_en_5.1.2_3.0_1694787983867.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_vsrinivas","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_vsrinivas", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_vsrinivas| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/vsrinivas/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_whole_word_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_whole_word_en.md new file mode 100644 index 00000000000000..6998c4d2df35c7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_whole_word_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_whole_word DistilBertEmbeddings from PhysHunter +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_whole_word +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_whole_word` is a English model originally trained by PhysHunter. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_whole_word_en_5.1.2_3.0_1694773100332.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_whole_word_en_5.1.2_3.0_1694773100332.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_whole_word","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_whole_word", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_whole_word| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/PhysHunter/distilbert-base-uncased-finetuned-imdb-whole-word \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_wjbmattingly_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_wjbmattingly_en.md new file mode 100644 index 00000000000000..932dfdf7b1c789 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_wjbmattingly_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_wjbmattingly DistilBertEmbeddings from wjbmattingly +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_wjbmattingly +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_wjbmattingly` is a English model originally trained by wjbmattingly. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_wjbmattingly_en_5.1.2_3.0_1694786512902.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_wjbmattingly_en_5.1.2_3.0_1694786512902.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_wjbmattingly","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_wjbmattingly", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_wjbmattingly| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/wjbmattingly/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_y_haneji_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_y_haneji_en.md new file mode 100644 index 00000000000000..765c2547379625 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_y_haneji_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_y_haneji DistilBertEmbeddings from Y-Haneji +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_y_haneji +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_y_haneji` is a English model originally trained by Y-Haneji. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_y_haneji_en_5.1.2_3.0_1694779145507.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_y_haneji_en_5.1.2_3.0_1694779145507.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_y_haneji","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_y_haneji", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_y_haneji| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Y-Haneji/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_yangwooko_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_yangwooko_en.md new file mode 100644 index 00000000000000..4ff6d48920795c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_yangwooko_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_yangwooko DistilBertEmbeddings from yangwooko +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_yangwooko +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_yangwooko` is a English model originally trained by yangwooko. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_yangwooko_en_5.1.2_3.0_1694776915854.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_yangwooko_en_5.1.2_3.0_1694776915854.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_yangwooko","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_yangwooko", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_yangwooko| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/yangwooko/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_yuto01_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_yuto01_en.md new file mode 100644 index 00000000000000..54c7b28979c107 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_imdb_yuto01_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_imdb_yuto01 DistilBertEmbeddings from Yuto01 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_imdb_yuto01 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_imdb_yuto01` is a English model originally trained by Yuto01. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_yuto01_en_5.1.2_3.0_1694789487678.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_imdb_yuto01_en_5.1.2_3.0_1694789487678.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_imdb_yuto01","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_imdb_yuto01", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_imdb_yuto01| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Yuto01/distilbert-base-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ivr_finetuned_ivr_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ivr_finetuned_ivr_en.md new file mode 100644 index 00000000000000..5bb26cad9437d5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_ivr_finetuned_ivr_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_ivr_finetuned_ivr DistilBertEmbeddings from khubaib +author: John Snow Labs +name: distilbert_base_uncased_finetuned_ivr_finetuned_ivr +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_ivr_finetuned_ivr` is a English model originally trained by khubaib. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_ivr_finetuned_ivr_en_5.1.2_3.0_1694776652350.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_ivr_finetuned_ivr_en_5.1.2_3.0_1694776652350.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_ivr_finetuned_ivr","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_ivr_finetuned_ivr", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_ivr_finetuned_ivr| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/khubaib/distilbert-base-uncased-finetuned-ivr-finetuned-ivr \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_kintweetse_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_kintweetse_en.md new file mode 100644 index 00000000000000..28f11009faeec0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_kintweetse_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_kintweetse DistilBertEmbeddings from RogerB +author: John Snow Labs +name: distilbert_base_uncased_finetuned_kintweetse +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_kintweetse` is a English model originally trained by RogerB. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_kintweetse_en_5.1.2_3.0_1694773642871.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_kintweetse_en_5.1.2_3.0_1694773642871.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_kintweetse","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_kintweetse", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_kintweetse| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/RogerB/distilbert-base-uncased-finetuned-kintweetsE \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_mlm_1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_mlm_1_en.md new file mode 100644 index 00000000000000..c9f7956e876fab --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_mlm_1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_mlm_1 DistilBertEmbeddings from aarroonn22 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_mlm_1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_mlm_1` is a English model originally trained by aarroonn22. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_mlm_1_en_5.1.2_3.0_1694772083071.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_mlm_1_en_5.1.2_3.0_1694772083071.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_mlm_1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_mlm_1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_mlm_1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/aarroonn22/distilbert-base-uncased-finetuned-mlm-1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_mlm_2_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_mlm_2_en.md new file mode 100644 index 00000000000000..0b03bbfd1628c5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_mlm_2_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_mlm_2 DistilBertEmbeddings from aarroonn22 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_mlm_2 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_mlm_2` is a English model originally trained by aarroonn22. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_mlm_2_en_5.1.2_3.0_1694770824986.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_mlm_2_en_5.1.2_3.0_1694770824986.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_mlm_2","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_mlm_2", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_mlm_2| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/aarroonn22/distilbert-base-uncased-finetuned-mlm-2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_nitro_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_nitro_en.md new file mode 100644 index 00000000000000..e0494c826755ce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_nitro_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_nitro DistilBertEmbeddings from dieexbr +author: John Snow Labs +name: distilbert_base_uncased_finetuned_nitro +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_nitro` is a English model originally trained by dieexbr. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_nitro_en_5.1.2_3.0_1694771823890.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_nitro_en_5.1.2_3.0_1694771823890.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_nitro","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_nitro", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_nitro| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dieexbr/distilbert-base-uncased-finetuned-nitro \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outoh_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outoh_en.md new file mode 100644 index 00000000000000..2f0bf97fda503e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outoh_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_outoh DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_outoh +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_outoh` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_outoh_en_5.1.2_3.0_1694779309949.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_outoh_en_5.1.2_3.0_1694779309949.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_outoh","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_outoh", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_outoh| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-outoH \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_en.md new file mode 100644 index 00000000000000..d85783ca467698 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_outop DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_outop +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_outop` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_outop_en_5.1.2_3.0_1694779414180.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_outop_en_5.1.2_3.0_1694779414180.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_outop","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_outop", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_outop| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-outop \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_j_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_j_en.md new file mode 100644 index 00000000000000..0a6350b9159fc5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_j_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_outop_j DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_outop_j +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_outop_j` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_outop_j_en_5.1.2_3.0_1694779643765.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_outop_j_en_5.1.2_3.0_1694779643765.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_outop_j","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_outop_j", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_outop_j| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-outop-J \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_y_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_y_en.md new file mode 100644 index 00000000000000..7ac829c6411954 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_outop_y_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_outop_y DistilBertEmbeddings from himanimaheshwari3 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_outop_y +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_outop_y` is a English model originally trained by himanimaheshwari3. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_outop_y_en_5.1.2_3.0_1694779519036.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_outop_y_en_5.1.2_3.0_1694779519036.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_outop_y","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_outop_y", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_outop_y| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/himanimaheshwari3/distilbert-base-uncased-finetuned-outop-y \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_preprint_full_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_preprint_full_en.md new file mode 100644 index 00000000000000..537f30f2a256de --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_preprint_full_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_preprint_full DistilBertEmbeddings from vamads +author: John Snow Labs +name: distilbert_base_uncased_finetuned_preprint_full +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_preprint_full` is a English model originally trained by vamads. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_preprint_full_en_5.1.2_3.0_1694780135347.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_preprint_full_en_5.1.2_3.0_1694780135347.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_preprint_full","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_preprint_full", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_preprint_full| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/vamads/distilbert-base-uncased-finetuned-preprint_full \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_provenances_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_provenances_en.md new file mode 100644 index 00000000000000..96df623755d907 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_provenances_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_provenances DistilBertEmbeddings from RiccardoGvn +author: John Snow Labs +name: distilbert_base_uncased_finetuned_provenances +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_provenances` is a English model originally trained by RiccardoGvn. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_provenances_en_5.1.2_3.0_1694781872135.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_provenances_en_5.1.2_3.0_1694781872135.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_provenances","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_provenances", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_provenances| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/RiccardoGvn/distilbert-base-uncased-finetuned-provenances \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_provenances_finetuned_provenances_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_provenances_finetuned_provenances_en.md new file mode 100644 index 00000000000000..2e0bc5c4ca3205 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_provenances_finetuned_provenances_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_provenances_finetuned_provenances DistilBertEmbeddings from RiccardoGvn +author: John Snow Labs +name: distilbert_base_uncased_finetuned_provenances_finetuned_provenances +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_provenances_finetuned_provenances` is a English model originally trained by RiccardoGvn. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_provenances_finetuned_provenances_en_5.1.2_3.0_1694781997921.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_provenances_finetuned_provenances_en_5.1.2_3.0_1694781997921.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_provenances_finetuned_provenances","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_provenances_finetuned_provenances", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_provenances_finetuned_provenances| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/RiccardoGvn/distilbert-base-uncased-finetuned-provenances-finetuned-provenances \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_rap_lyrics_v1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_rap_lyrics_v1_en.md new file mode 100644 index 00000000000000..a6db78786dcad1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_rap_lyrics_v1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_rap_lyrics_v1 DistilBertEmbeddings from peteryushunli +author: John Snow Labs +name: distilbert_base_uncased_finetuned_rap_lyrics_v1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_rap_lyrics_v1` is a English model originally trained by peteryushunli. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_rap_lyrics_v1_en_5.1.2_3.0_1694788210807.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_rap_lyrics_v1_en_5.1.2_3.0_1694788210807.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_rap_lyrics_v1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_rap_lyrics_v1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_rap_lyrics_v1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/peteryushunli/distilbert-base-uncased-finetuned-rap-lyrics-v1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_recipe_accelerate_1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_recipe_accelerate_1_en.md new file mode 100644 index 00000000000000..2c0e27bcab0f19 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_recipe_accelerate_1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_recipe_accelerate_1 DistilBertEmbeddings from CennetOguz +author: John Snow Labs +name: distilbert_base_uncased_finetuned_recipe_accelerate_1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_recipe_accelerate_1` is a English model originally trained by CennetOguz. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_recipe_accelerate_1_en_5.1.2_3.0_1694770672733.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_recipe_accelerate_1_en_5.1.2_3.0_1694770672733.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_recipe_accelerate_1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_recipe_accelerate_1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_recipe_accelerate_1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/CennetOguz/distilbert-base-uncased-finetuned-recipe-accelerate-1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_recipe_accelerate_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_recipe_accelerate_en.md new file mode 100644 index 00000000000000..d64ec039e6bc80 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_recipe_accelerate_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_recipe_accelerate DistilBertEmbeddings from CennetOguz +author: John Snow Labs +name: distilbert_base_uncased_finetuned_recipe_accelerate +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_recipe_accelerate` is a English model originally trained by CennetOguz. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_recipe_accelerate_en_5.1.2_3.0_1694770774708.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_recipe_accelerate_en_5.1.2_3.0_1694770774708.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_recipe_accelerate","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_recipe_accelerate", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_recipe_accelerate| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/CennetOguz/distilbert-base-uncased-finetuned-recipe-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_speeches_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_speeches_en.md new file mode 100644 index 00000000000000..01ced0e38ca9fe --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_speeches_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_speeches DistilBertEmbeddings from peterday +author: John Snow Labs +name: distilbert_base_uncased_finetuned_speeches +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_speeches` is a English model originally trained by peterday. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_speeches_en_5.1.2_3.0_1694770816356.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_speeches_en_5.1.2_3.0_1694770816356.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_speeches","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_speeches", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_speeches| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/peterday/distilbert-base-uncased-finetuned-speeches \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz_en.md new file mode 100644 index 00000000000000..c76388f0a9c3c8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz DistilBertEmbeddings from BatuhanYilmaz +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz` is a English model originally trained by BatuhanYilmaz. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz_en_5.1.2_3.0_1694770351064.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz_en_5.1.2_3.0_1694770351064.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_batuhanyilmaz| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/BatuhanYilmaz/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg_en.md new file mode 100644 index 00000000000000..e50ed6892b1b27 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg DistilBertEmbeddings from bellawanggg +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg` is a English model originally trained by bellawanggg. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg_en_5.1.2_3.0_1694771192012.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg_en_5.1.2_3.0_1694771192012.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_bellawanggg| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/bellawanggg/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db_en.md new file mode 100644 index 00000000000000..19254d4efb38ce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db DistilBertEmbeddings from coreyabs-db +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db` is a English model originally trained by coreyabs-db. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db_en_5.1.2_3.0_1694781671387.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db_en_5.1.2_3.0_1694781671387.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_coreyabs_db| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/coreyabs-db/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_dchung117_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_dchung117_en.md new file mode 100644 index 00000000000000..3e0cc2060164b7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_dchung117_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_dchung117 DistilBertEmbeddings from dchung117 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_dchung117 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_dchung117` is a English model originally trained by dchung117. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_dchung117_en_5.1.2_3.0_1694788118641.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_dchung117_en_5.1.2_3.0_1694788118641.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_dchung117","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_dchung117", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_dchung117| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dchung117/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_dkimds_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_dkimds_en.md new file mode 100644 index 00000000000000..77e28d5e954cc1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_dkimds_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_dkimds DistilBertEmbeddings from dkimds +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_dkimds +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_dkimds` is a English model originally trained by dkimds. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_dkimds_en_5.1.2_3.0_1694786923235.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_dkimds_en_5.1.2_3.0_1694786923235.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_dkimds","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_dkimds", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_dkimds| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dkimds/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi_en.md new file mode 100644 index 00000000000000..27ef6d217bbcd7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi DistilBertEmbeddings from fadliaulawi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi` is a English model originally trained by fadliaulawi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi_en_5.1.2_3.0_1694777976444.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi_en_5.1.2_3.0_1694777976444.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_fadliaulawi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/fadliaulawi/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989_en.md new file mode 100644 index 00000000000000..f2312e27b7f8e3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989 DistilBertEmbeddings from gautam1989 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989` is a English model originally trained by gautam1989. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989_en_5.1.2_3.0_1694773530136.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989_en_5.1.2_3.0_1694773530136.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_gautam1989| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/gautam1989/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_gostrive_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_gostrive_en.md new file mode 100644 index 00000000000000..75b429d50c86ab --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_gostrive_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_gostrive DistilBertEmbeddings from gostrive +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_gostrive +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_gostrive` is a English model originally trained by gostrive. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_gostrive_en_5.1.2_3.0_1694782689611.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_gostrive_en_5.1.2_3.0_1694782689611.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_gostrive","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_gostrive", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_gostrive| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/gostrive/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_guoguo_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_guoguo_en.md new file mode 100644 index 00000000000000..5c932c1ae45321 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_guoguo_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_guoguo DistilBertEmbeddings from guoguo +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_guoguo +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_guoguo` is a English model originally trained by guoguo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_guoguo_en_5.1.2_3.0_1694784353246.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_guoguo_en_5.1.2_3.0_1694784353246.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_guoguo","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_guoguo", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_guoguo| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/guoguo/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr_en.md new file mode 100644 index 00000000000000..6d0b52804d9bf6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr DistilBertEmbeddings from iotengtr +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr` is a English model originally trained by iotengtr. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr_en_5.1.2_3.0_1694774783675.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr_en_5.1.2_3.0_1694774783675.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_iotengtr| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/iotengtr/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81_en.md new file mode 100644 index 00000000000000..4707af5be751e6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81 DistilBertEmbeddings from juancopi81 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81` is a English model originally trained by juancopi81. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81_en_5.1.2_3.0_1694779999978.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81_en_5.1.2_3.0_1694779999978.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_juancopi81| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/juancopi81/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea_en.md new file mode 100644 index 00000000000000..ca6d920b37cc4f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea DistilBertEmbeddings from jwlovetea +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea` is a English model originally trained by jwlovetea. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea_en_5.1.2_3.0_1694790258197.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea_en_5.1.2_3.0_1694790258197.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_jwlovetea| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jwlovetea/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn_en.md new file mode 100644 index 00000000000000..b799b235ed2df7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn DistilBertEmbeddings from lakecrimsonn +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn` is a English model originally trained by lakecrimsonn. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn_en_5.1.2_3.0_1694775410500.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn_en_5.1.2_3.0_1694775410500.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_lakecrimsonn| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/lakecrimsonn/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_luzimu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_luzimu_en.md new file mode 100644 index 00000000000000..201520baae29e2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_luzimu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_luzimu DistilBertEmbeddings from luzimu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_luzimu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_luzimu` is a English model originally trained by luzimu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_luzimu_en_5.1.2_3.0_1694783536406.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_luzimu_en_5.1.2_3.0_1694783536406.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_luzimu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_luzimu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_luzimu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/luzimu/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_maseiya_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_maseiya_en.md new file mode 100644 index 00000000000000..6aaf7db41b68e6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_maseiya_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_maseiya DistilBertEmbeddings from maseiya +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_maseiya +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_maseiya` is a English model originally trained by maseiya. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_maseiya_en_5.1.2_3.0_1694770328657.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_maseiya_en_5.1.2_3.0_1694770328657.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_maseiya","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_maseiya", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_maseiya| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/maseiya/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_mbateman_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_mbateman_en.md new file mode 100644 index 00000000000000..e117378fd6db5b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_mbateman_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_mbateman DistilBertEmbeddings from mbateman +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_mbateman +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_mbateman` is a English model originally trained by mbateman. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_mbateman_en_5.1.2_3.0_1694782120527.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_mbateman_en_5.1.2_3.0_1694782120527.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_mbateman","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_mbateman", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_mbateman| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/mbateman/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob_en.md new file mode 100644 index 00000000000000..c947fab2d8e8ce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob DistilBertEmbeddings from miesnerjacob +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob` is a English model originally trained by miesnerjacob. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob_en_5.1.2_3.0_1694774420966.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob_en_5.1.2_3.0_1694774420966.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_miesnerjacob| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/miesnerjacob/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi_en.md new file mode 100644 index 00000000000000..925e071a5e5068 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi DistilBertEmbeddings from nicolacandussi +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi` is a English model originally trained by nicolacandussi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi_en_5.1.2_3.0_1694792078563.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi_en_5.1.2_3.0_1694792078563.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_nicolacandussi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/nicolacandussi/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_nugget00_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_nugget00_en.md new file mode 100644 index 00000000000000..61660c170d082c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_nugget00_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_nugget00 DistilBertEmbeddings from nugget00 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_nugget00 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_nugget00` is a English model originally trained by nugget00. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_nugget00_en_5.1.2_3.0_1694788315308.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_nugget00_en_5.1.2_3.0_1694788315308.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_nugget00","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_nugget00", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_nugget00| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/nugget00/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero_en.md new file mode 100644 index 00000000000000..32d5a19e816465 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero DistilBertEmbeddings from osanseviero +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero` is a English model originally trained by osanseviero. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero_en_5.1.2_3.0_1694787328705.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero_en_5.1.2_3.0_1694787328705.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_osanseviero| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/osanseviero/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu_en.md new file mode 100644 index 00000000000000..93128e31c9cbaf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu DistilBertEmbeddings from peterhsu +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu` is a English model originally trained by peterhsu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu_en_5.1.2_3.0_1694787941415.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu_en_5.1.2_3.0_1694787941415.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_peterhsu| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/peterhsu/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_physhunter_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_physhunter_en.md new file mode 100644 index 00000000000000..a5dd3aaecc4b28 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_physhunter_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_physhunter DistilBertEmbeddings from PhysHunter +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_physhunter +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_physhunter` is a English model originally trained by PhysHunter. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_physhunter_en_5.1.2_3.0_1694776775566.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_physhunter_en_5.1.2_3.0_1694776775566.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_physhunter","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_physhunter", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_physhunter| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/PhysHunter/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake_en.md new file mode 100644 index 00000000000000..6124c05c388d9f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake DistilBertEmbeddings from runningsnake +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake` is a English model originally trained by runningsnake. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake_en_5.1.2_3.0_1694782116286.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake_en_5.1.2_3.0_1694782116286.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_runningsnake| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/runningsnake/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo_en.md new file mode 100644 index 00000000000000..a26a62436e8e37 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo DistilBertEmbeddings from SayaEndo +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo` is a English model originally trained by SayaEndo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo_en_5.1.2_3.0_1694781746406.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo_en_5.1.2_3.0_1694781746406.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_sayaendo| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/SayaEndo/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sebastians_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sebastians_en.md new file mode 100644 index 00000000000000..7880a9faf7bb14 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sebastians_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_sebastians DistilBertEmbeddings from SebastianS +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_sebastians +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_sebastians` is a English model originally trained by SebastianS. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sebastians_en_5.1.2_3.0_1694772917775.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sebastians_en_5.1.2_3.0_1694772917775.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sebastians","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sebastians", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_sebastians| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/SebastianS/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sgr23_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sgr23_en.md new file mode 100644 index 00000000000000..efbac5bdd51fad --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sgr23_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_sgr23 DistilBertEmbeddings from sgr23 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_sgr23 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_sgr23` is a English model originally trained by sgr23. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sgr23_en_5.1.2_3.0_1694784756753.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sgr23_en_5.1.2_3.0_1694784756753.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sgr23","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sgr23", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_sgr23| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/sgr23/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41_en.md new file mode 100644 index 00000000000000..6ca1c0b309f589 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41 DistilBertEmbeddings from ShadowTwin41 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41` is a English model originally trained by ShadowTwin41. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41_en_5.1.2_3.0_1694788124987.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41_en_5.1.2_3.0_1694788124987.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_shadowtwin41| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ShadowTwin41/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_soduhh_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_soduhh_en.md new file mode 100644 index 00000000000000..ba93a526c82f02 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_soduhh_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_soduhh DistilBertEmbeddings from soduhh +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_soduhh +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_soduhh` is a English model originally trained by soduhh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_soduhh_en_5.1.2_3.0_1694774128556.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_soduhh_en_5.1.2_3.0_1694774128556.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_soduhh","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_soduhh", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_soduhh| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/soduhh/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sofa566_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sofa566_en.md new file mode 100644 index 00000000000000..b830706876afd0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sofa566_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_sofa566 DistilBertEmbeddings from sofa566 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_sofa566 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_sofa566` is a English model originally trained by sofa566. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sofa566_en_5.1.2_3.0_1694781170986.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sofa566_en_5.1.2_3.0_1694781170986.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sofa566","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sofa566", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_sofa566| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/sofa566/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sonny_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sonny_en.md new file mode 100644 index 00000000000000..ed7d934754d984 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sonny_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_sonny DistilBertEmbeddings from Sonny +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_sonny +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_sonny` is a English model originally trained by Sonny. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sonny_en_5.1.2_3.0_1694779487811.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sonny_en_5.1.2_3.0_1694779487811.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sonny","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sonny", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_sonny| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Sonny/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sophon_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sophon_en.md new file mode 100644 index 00000000000000..8ae491e84cc761 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_sophon_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_sophon DistilBertEmbeddings from Sophon +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_sophon +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_sophon` is a English model originally trained by Sophon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sophon_en_5.1.2_3.0_1694772344487.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_sophon_en_5.1.2_3.0_1694772344487.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sophon","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_sophon", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_sophon| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Sophon/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829_en.md new file mode 100644 index 00000000000000..b222b6dd23a283 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829 DistilBertEmbeddings from suzuki0829 +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829` is a English model originally trained by suzuki0829. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829_en_5.1.2_3.0_1694770510510.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829_en_5.1.2_3.0_1694770510510.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_suzuki0829| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/suzuki0829/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_thabet_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_thabet_en.md new file mode 100644 index 00000000000000..7a9acfa63cb213 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_thabet_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_squad_d5716d28_thabet DistilBertEmbeddings from Thabet +author: John Snow Labs +name: distilbert_base_uncased_finetuned_squad_d5716d28_thabet +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_squad_d5716d28_thabet` is a English model originally trained by Thabet. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_thabet_en_5.1.2_3.0_1694784973757.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_thabet_en_5.1.2_3.0_1694784973757.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_thabet","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_squad_d5716d28_thabet", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_squad_d5716d28_thabet| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Thabet/distilbert-base-uncased-finetuned-squad-d5716d28 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_ysugawa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_ysugawa_en.md index 1926befd573ad4..319879f624e735 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_ysugawa_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_squad_d5716d28_ysugawa_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_ysugawa_en_5.1.2_3.0_1694736922524.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_ysugawa_en_5.1.2_3.0_1694736922524.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_ysugawa_en_5.1.2_3.0_1694770212287.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_squad_d5716d28_ysugawa_en_5.1.2_3.0_1694770212287.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_test_headline_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_test_headline_en.md new file mode 100644 index 00000000000000..f01c79160c471c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_test_headline_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_test_headline DistilBertEmbeddings from lucypallent +author: John Snow Labs +name: distilbert_base_uncased_finetuned_test_headline +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_test_headline` is a English model originally trained by lucypallent. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_test_headline_en_5.1.2_3.0_1694790033469.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_test_headline_en_5.1.2_3.0_1694790033469.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_test_headline","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_test_headline", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_test_headline| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/lucypallent/distilbert-base-uncased-finetuned-test-headline \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_tweet_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_tweet_en.md new file mode 100644 index 00000000000000..cb54b422676481 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_tweet_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_tweet DistilBertEmbeddings from shreyasdatar +author: John Snow Labs +name: distilbert_base_uncased_finetuned_tweet +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_tweet` is a English model originally trained by shreyasdatar. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_tweet_en_5.1.2_3.0_1694783838766.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_tweet_en_5.1.2_3.0_1694783838766.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_tweet","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_tweet", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_tweet| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/shreyasdatar/distilbert-base-uncased-finetuned-tweet \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_vk_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_vk_en.md new file mode 100644 index 00000000000000..b27a7654af3211 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_vk_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_vk DistilBertEmbeddings from bruhwalkk +author: John Snow Labs +name: distilbert_base_uncased_finetuned_vk +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_vk` is a English model originally trained by bruhwalkk. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_vk_en_5.1.2_3.0_1694780625605.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_vk_en_5.1.2_3.0_1694780625605.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_vk","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_vk", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_vk| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.0 MB| + +## References + +https://huggingface.co/bruhwalkk/distilbert-base-uncased-finetuned-vk \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_wb_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_wb_en.md new file mode 100644 index 00000000000000..d2e6b25744d635 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_wb_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_wb DistilBertEmbeddings from alexskrn +author: John Snow Labs +name: distilbert_base_uncased_finetuned_wb +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_wb` is a English model originally trained by alexskrn. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_wb_en_5.1.2_3.0_1694782258713.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_wb_en_5.1.2_3.0_1694782258713.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_wb","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_wb", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_wb| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/alexskrn/distilbert-base-uncased-finetuned-wb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_wos_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_wos_en.md new file mode 100644 index 00000000000000..c6ede77dc6af52 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_finetuned_wos_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_finetuned_wos DistilBertEmbeddings from alvin-wen +author: John Snow Labs +name: distilbert_base_uncased_finetuned_wos +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_finetuned_wos` is a English model originally trained by alvin-wen. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_wos_en_5.1.2_3.0_1694782853873.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_finetuned_wos_en_5.1.2_3.0_1694782853873.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_finetuned_wos","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_finetuned_wos", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_finetuned_wos| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/alvin-wen/distilbert-base-uncased-finetuned-wos \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_holocaust_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_holocaust_en.md new file mode 100644 index 00000000000000..39a447f9a36385 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_holocaust_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_holocaust DistilBertEmbeddings from wjbmattingly +author: John Snow Labs +name: distilbert_base_uncased_holocaust +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_holocaust` is a English model originally trained by wjbmattingly. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_holocaust_en_5.1.2_3.0_1694786616427.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_holocaust_en_5.1.2_3.0_1694786616427.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_holocaust","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_holocaust", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_holocaust| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/wjbmattingly/distilbert-base-uncased-holocaust \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_accelerate_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_accelerate_en.md new file mode 100644 index 00000000000000..13a0359616d1d0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_accelerate_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_imdb_accelerate DistilBertEmbeddings from hieule +author: John Snow Labs +name: distilbert_base_uncased_imdb_accelerate +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_imdb_accelerate` is a English model originally trained by hieule. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_imdb_accelerate_en_5.1.2_3.0_1694784667459.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_imdb_accelerate_en_5.1.2_3.0_1694784667459.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_imdb_accelerate","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_imdb_accelerate", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_imdb_accelerate| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/hieule/distilbert-base-uncased-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_disbert1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_disbert1_en.md new file mode 100644 index 00000000000000..698d45123a8c62 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_disbert1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_imdb_disbert1 DistilBertEmbeddings from Billwzl +author: John Snow Labs +name: distilbert_base_uncased_imdb_disbert1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_imdb_disbert1` is a English model originally trained by Billwzl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_imdb_disbert1_en_5.1.2_3.0_1694783463877.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_imdb_disbert1_en_5.1.2_3.0_1694783463877.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_imdb_disbert1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_imdb_disbert1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_imdb_disbert1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.0 MB| + +## References + +https://huggingface.co/Billwzl/distilbert-base-uncased-IMDB_disbert1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_distilbert_en.md new file mode 100644 index 00000000000000..02caca63fcd510 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_imdb_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_imdb_distilbert DistilBertEmbeddings from Billwzl +author: John Snow Labs +name: distilbert_base_uncased_imdb_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_imdb_distilbert` is a English model originally trained by Billwzl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_imdb_distilbert_en_5.1.2_3.0_1694782933769.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_imdb_distilbert_en_5.1.2_3.0_1694782933769.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_imdb_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_imdb_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_imdb_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Billwzl/distilbert-base-uncased-IMDB_distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_issues_128_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_issues_128_en.md new file mode 100644 index 00000000000000..c20f2d91d20f46 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_issues_128_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_issues_128 DistilBertEmbeddings from Chrispfield +author: John Snow Labs +name: distilbert_base_uncased_issues_128 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_issues_128` is a English model originally trained by Chrispfield. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_issues_128_en_5.1.2_3.0_1694784972786.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_issues_128_en_5.1.2_3.0_1694784972786.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_issues_128","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_issues_128", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_issues_128| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Chrispfield/distilbert-base-uncased-issues-128 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_linkedin_domain_adaptation_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_linkedin_domain_adaptation_en.md new file mode 100644 index 00000000000000..d27eeedeb45238 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_linkedin_domain_adaptation_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_linkedin_domain_adaptation DistilBertEmbeddings from algiraldohe +author: John Snow Labs +name: distilbert_base_uncased_linkedin_domain_adaptation +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_linkedin_domain_adaptation` is a English model originally trained by algiraldohe. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_linkedin_domain_adaptation_en_5.1.2_3.0_1694772620399.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_linkedin_domain_adaptation_en_5.1.2_3.0_1694772620399.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_linkedin_domain_adaptation","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_linkedin_domain_adaptation", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_linkedin_domain_adaptation| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/algiraldohe/distilbert-base-uncased-linkedin-domain-adaptation \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_malayalam_arxiv_papers_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_malayalam_arxiv_papers_en.md new file mode 100644 index 00000000000000..4348333d106e19 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_malayalam_arxiv_papers_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_malayalam_arxiv_papers DistilBertEmbeddings from aalksii +author: John Snow Labs +name: distilbert_base_uncased_malayalam_arxiv_papers +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_malayalam_arxiv_papers` is a English model originally trained by aalksii. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_malayalam_arxiv_papers_en_5.1.2_3.0_1694783989229.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_malayalam_arxiv_papers_en_5.1.2_3.0_1694783989229.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_malayalam_arxiv_papers","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_malayalam_arxiv_papers", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_malayalam_arxiv_papers| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/aalksii/distilbert-base-uncased-ml-arxiv-papers \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mask_accelerate_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mask_accelerate_en.md new file mode 100644 index 00000000000000..5e083c5e694835 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mask_accelerate_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_mask_accelerate DistilBertEmbeddings from xiannvhh +author: John Snow Labs +name: distilbert_base_uncased_mask_accelerate +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_mask_accelerate` is a English model originally trained by xiannvhh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mask_accelerate_en_5.1.2_3.0_1694785625253.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mask_accelerate_en_5.1.2_3.0_1694785625253.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_mask_accelerate","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_mask_accelerate", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_mask_accelerate| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/xiannvhh/distilbert-base-uncased-mask-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mask_finetuned_imdb_v1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mask_finetuned_imdb_v1_en.md new file mode 100644 index 00000000000000..c88a0d0e3f6866 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mask_finetuned_imdb_v1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_mask_finetuned_imdb_v1 DistilBertEmbeddings from kaiku03 +author: John Snow Labs +name: distilbert_base_uncased_mask_finetuned_imdb_v1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_mask_finetuned_imdb_v1` is a English model originally trained by kaiku03. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mask_finetuned_imdb_v1_en_5.1.2_3.0_1694788413645.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mask_finetuned_imdb_v1_en_5.1.2_3.0_1694788413645.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_mask_finetuned_imdb_v1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_mask_finetuned_imdb_v1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_mask_finetuned_imdb_v1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/kaiku03/distilbert-base-uncased-mask-finetuned-imdb_v1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mlm_scirepeval_fos_chemistry_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mlm_scirepeval_fos_chemistry_en.md new file mode 100644 index 00000000000000..990cf1b3846257 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mlm_scirepeval_fos_chemistry_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_mlm_scirepeval_fos_chemistry DistilBertEmbeddings from jonas-luehrs +author: John Snow Labs +name: distilbert_base_uncased_mlm_scirepeval_fos_chemistry +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_mlm_scirepeval_fos_chemistry` is a English model originally trained by jonas-luehrs. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mlm_scirepeval_fos_chemistry_en_5.1.2_3.0_1694784976059.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mlm_scirepeval_fos_chemistry_en_5.1.2_3.0_1694784976059.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_mlm_scirepeval_fos_chemistry","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_mlm_scirepeval_fos_chemistry", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_mlm_scirepeval_fos_chemistry| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jonas-luehrs/distilbert-base-uncased-MLM-scirepeval_fos_chemistry \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mlm_tamil_local_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mlm_tamil_local_en.md new file mode 100644 index 00000000000000..1a86dcf2ea1831 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_mlm_tamil_local_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_mlm_tamil_local DistilBertEmbeddings from medhabi +author: John Snow Labs +name: distilbert_base_uncased_mlm_tamil_local +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_mlm_tamil_local` is a English model originally trained by medhabi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mlm_tamil_local_en_5.1.2_3.0_1694788852384.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_mlm_tamil_local_en_5.1.2_3.0_1694788852384.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_mlm_tamil_local","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_mlm_tamil_local", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_mlm_tamil_local| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/medhabi/distilbert-base-uncased-mlm-ta-local \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_scratch_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_scratch_en.md new file mode 100644 index 00000000000000..94c2c4fa2f0145 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_scratch_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_scratch DistilBertEmbeddings from hieule +author: John Snow Labs +name: distilbert_base_uncased_scratch +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_scratch` is a English model originally trained by hieule. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_scratch_en_5.1.2_3.0_1694784563353.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_scratch_en_5.1.2_3.0_1694784563353.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_scratch","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_scratch", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_scratch| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/hieule/distilbert-base-uncased-scratch \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_80_1x4_block_pruneofa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_80_1x4_block_pruneofa_en.md new file mode 100644 index 00000000000000..d42b5dddc0ba91 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_80_1x4_block_pruneofa_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_sparse_80_1x4_block_pruneofa DistilBertEmbeddings from Intel +author: John Snow Labs +name: distilbert_base_uncased_sparse_80_1x4_block_pruneofa +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_sparse_80_1x4_block_pruneofa` is a English model originally trained by Intel. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_sparse_80_1x4_block_pruneofa_en_5.1.2_3.0_1694785612750.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_sparse_80_1x4_block_pruneofa_en_5.1.2_3.0_1694785612750.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_sparse_80_1x4_block_pruneofa","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_sparse_80_1x4_block_pruneofa", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_sparse_80_1x4_block_pruneofa| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|136.5 MB| + +## References + +https://huggingface.co/Intel/distilbert-base-uncased-sparse-80-1x4-block-pruneofa \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_85_unstructured_pruneofa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_85_unstructured_pruneofa_en.md new file mode 100644 index 00000000000000..a02bdabd658dce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_85_unstructured_pruneofa_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_sparse_85_unstructured_pruneofa DistilBertEmbeddings from Intel +author: John Snow Labs +name: distilbert_base_uncased_sparse_85_unstructured_pruneofa +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_sparse_85_unstructured_pruneofa` is a English model originally trained by Intel. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_sparse_85_unstructured_pruneofa_en_5.1.2_3.0_1694778491947.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_sparse_85_unstructured_pruneofa_en_5.1.2_3.0_1694778491947.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_sparse_85_unstructured_pruneofa","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_sparse_85_unstructured_pruneofa", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_sparse_85_unstructured_pruneofa| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|132.5 MB| + +## References + +https://huggingface.co/Intel/distilbert-base-uncased-sparse-85-unstructured-pruneofa \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_90_unstructured_pruneofa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_90_unstructured_pruneofa_en.md new file mode 100644 index 00000000000000..5a59934e1cf1d8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_sparse_90_unstructured_pruneofa_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_sparse_90_unstructured_pruneofa DistilBertEmbeddings from Intel +author: John Snow Labs +name: distilbert_base_uncased_sparse_90_unstructured_pruneofa +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_sparse_90_unstructured_pruneofa` is a English model originally trained by Intel. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_sparse_90_unstructured_pruneofa_en_5.1.2_3.0_1694778619456.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_sparse_90_unstructured_pruneofa_en_5.1.2_3.0_1694778619456.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_sparse_90_unstructured_pruneofa","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_sparse_90_unstructured_pruneofa", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_sparse_90_unstructured_pruneofa| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|123.3 MB| + +## References + +https://huggingface.co/Intel/distilbert-base-uncased-sparse-90-unstructured-pruneofa \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_wholewordmasking_finetuned_imdb_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_wholewordmasking_finetuned_imdb_en.md new file mode 100644 index 00000000000000..809064db15d5be --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_base_uncased_wholewordmasking_finetuned_imdb_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_base_uncased_wholewordmasking_finetuned_imdb DistilBertEmbeddings from VanHoan +author: John Snow Labs +name: distilbert_base_uncased_wholewordmasking_finetuned_imdb +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_base_uncased_wholewordmasking_finetuned_imdb` is a English model originally trained by VanHoan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_wholewordmasking_finetuned_imdb_en_5.1.2_3.0_1694784099518.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_base_uncased_wholewordmasking_finetuned_imdb_en_5.1.2_3.0_1694784099518.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_base_uncased_wholewordmasking_finetuned_imdb","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_base_uncased_wholewordmasking_finetuned_imdb", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_base_uncased_wholewordmasking_finetuned_imdb| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/VanHoan/distilbert-base-uncased-WholeWordMasking-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_classification_eplorer_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_classification_eplorer_en.md new file mode 100644 index 00000000000000..26a254a4a3a7b5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_classification_eplorer_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_classification_eplorer DistilBertEmbeddings from edanigoben +author: John Snow Labs +name: distilbert_classification_eplorer +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_classification_eplorer` is a English model originally trained by edanigoben. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_classification_eplorer_en_5.1.2_3.0_1694778754715.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_classification_eplorer_en_5.1.2_3.0_1694778754715.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_classification_eplorer","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_classification_eplorer", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_classification_eplorer| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/edanigoben/distilbert-classification-eplorer \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_cmc_a8_h512_l4_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_cmc_a8_h512_l4_en.md new file mode 100644 index 00000000000000..744dc76b096790 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_cmc_a8_h512_l4_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_cmc_a8_h512_l4 DistilBertEmbeddings from levuloihust +author: John Snow Labs +name: distilbert_cmc_a8_h512_l4 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_cmc_a8_h512_l4` is a English model originally trained by levuloihust. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_cmc_a8_h512_l4_en_5.1.2_3.0_1694782904245.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_cmc_a8_h512_l4_en_5.1.2_3.0_1694782904245.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_cmc_a8_h512_l4","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_cmc_a8_h512_l4", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_cmc_a8_h512_l4| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|167.9 MB| + +## References + +https://huggingface.co/levuloihust/distilbert-cmc-A8-H512-L4 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_domain_adapted_ecomm_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_domain_adapted_ecomm_en.md new file mode 100644 index 00000000000000..ecfa2e4d18f441 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_domain_adapted_ecomm_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_domain_adapted_ecomm DistilBertEmbeddings from Kk2k +author: John Snow Labs +name: distilbert_domain_adapted_ecomm +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_domain_adapted_ecomm` is a English model originally trained by Kk2k. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_domain_adapted_ecomm_en_5.1.2_3.0_1694783099567.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_domain_adapted_ecomm_en_5.1.2_3.0_1694783099567.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_domain_adapted_ecomm","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_domain_adapted_ecomm", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_domain_adapted_ecomm| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/Kk2k/Distilbert_domain_adapted_ecomm \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_base_uncased_continued_training_medqa_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_base_uncased_continued_training_medqa_en.md new file mode 100644 index 00000000000000..886624345f6f39 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_base_uncased_continued_training_medqa_en.md @@ -0,0 +1,101 @@ +--- +layout: model +title: English Bert Embeddings model (from Shaier) +author: John Snow Labs +name: distilbert_embeddings_base_uncased_continued_training_medqa +date: 2023-09-15 +tags: [open_source, distilbert, distilbert_embeddings, distilbertformaskedlm, en, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `distilbert-base-uncased-continued_training-medqa` is a English model originally trained by `Shaier`. + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_base_uncased_continued_training_medqa_en_5.1.2_3.0_1694777575763.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_base_uncased_continued_training_medqa_en_5.1.2_3.0_1694777575763.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +documentAssembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("document") + +tokenizer = Tokenizer() \ + .setInputCols("document") \ + .setOutputCol("token") + +embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_base_uncased_continued_training_medqa","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("embeddings") \ + .setCaseSensitive(True) + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings]) + +data = spark.createDataFrame([["I love Spark-NLP"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_base_uncased_continued_training_medqa","en") + .setInputCols(Array("document", "token")) + .setOutputCol("embeddings") + .setCaseSensitive(True) + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings)) + +val data = Seq("I love Spark-NLP").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_embeddings_base_uncased_continued_training_medqa| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[sentence, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| +|Case sensitive:|false| + +## References + +References + +https://huggingface.co/Shaier/distilbert-base-uncased-continued_training-medqa \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_base_uncased_finetuned_imdb_accelerate_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_base_uncased_finetuned_imdb_accelerate_en.md new file mode 100644 index 00000000000000..3d3eba092e03a4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_base_uncased_finetuned_imdb_accelerate_en.md @@ -0,0 +1,101 @@ +--- +layout: model +title: English Bert Embeddings Cased model (from nrsmac) +author: John Snow Labs +name: distilbert_embeddings_base_uncased_finetuned_imdb_accelerate +date: 2023-09-15 +tags: [open_source, distilbert, distilbert_embeddings, distilbertformaskedlm, en, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `distilbert-base-uncased-finetuned-imdb-accelerate` is a English model originally trained by `nrsmac`. + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_base_uncased_finetuned_imdb_accelerate_en_5.1.2_3.0_1694779961580.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_base_uncased_finetuned_imdb_accelerate_en_5.1.2_3.0_1694779961580.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +documentAssembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("document") + +tokenizer = Tokenizer() \ + .setInputCols("document") \ + .setOutputCol("token") + +embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_base_uncased_finetuned_imdb_accelerate","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("embeddings") \ + .setCaseSensitive(True) + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings]) + +data = spark.createDataFrame([["I love Spark-NLP"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_base_uncased_finetuned_imdb_accelerate","en") + .setInputCols(Array("document", "token")) + .setOutputCol("embeddings") + .setCaseSensitive(True) + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings)) + +val data = Seq("I love Spark-NLP").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_embeddings_base_uncased_finetuned_imdb_accelerate| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[sentence, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| +|Case sensitive:|false| + +## References + +References + +https://huggingface.co/nrsmac/distilbert-base-uncased-finetuned-imdb-accelerate \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_bio_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_bio_cased_en.md new file mode 100644 index 00000000000000..9b96f3832a81fd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_bio_cased_en.md @@ -0,0 +1,101 @@ +--- +layout: model +title: English Bert Embeddings Cased model (from nlpie) +author: John Snow Labs +name: distilbert_embeddings_bio_cased +date: 2023-09-15 +tags: [open_source, distilbert, distilbert_embeddings, distilbertformaskedlm, en, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bio-distilbert-cased` is a English model originally trained by `nlpie`. + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_bio_cased_en_5.1.2_3.0_1694783708969.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_bio_cased_en_5.1.2_3.0_1694783708969.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +documentAssembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("document") + +tokenizer = Tokenizer() \ + .setInputCols("document") \ + .setOutputCol("token") + +embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_bio_cased","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("embeddings") \ + .setCaseSensitive(True) + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings]) + +data = spark.createDataFrame([["I love Spark-NLP"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_bio_cased","en") + .setInputCols(Array("document", "token")) + .setOutputCol("embeddings") + .setCaseSensitive(True) + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings)) + +val data = Seq("I love Spark-NLP").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_embeddings_bio_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[sentence, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|243.7 MB| +|Case sensitive:|false| + +## References + +References + +https://huggingface.co/nlpie/bio-distilbert-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_bio_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_bio_uncased_en.md new file mode 100644 index 00000000000000..f692d7bf074a8d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_bio_uncased_en.md @@ -0,0 +1,101 @@ +--- +layout: model +title: English Bert Embeddings model (from nlpie) +author: John Snow Labs +name: distilbert_embeddings_bio_uncased +date: 2023-09-15 +tags: [open_source, distilbert, distilbert_embeddings, distilbertformaskedlm, en, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bio-distilbert-uncased` is a English model originally trained by `nlpie`. + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_bio_uncased_en_5.1.2_3.0_1694783869030.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_bio_uncased_en_5.1.2_3.0_1694783869030.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +documentAssembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("document") + +tokenizer = Tokenizer() \ + .setInputCols("document") \ + .setOutputCol("token") + +embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_bio_uncased","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("embeddings") \ + .setCaseSensitive(True) + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings]) + +data = spark.createDataFrame([["I love Spark-NLP"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_bio_uncased","en") + .setInputCols(Array("document", "token")) + .setOutputCol("embeddings") + .setCaseSensitive(True) + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings)) + +val data = Seq("I love Spark-NLP").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_embeddings_bio_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[sentence, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| +|Case sensitive:|false| + +## References + +References + +https://huggingface.co/nlpie/bio-distilbert-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_clinical_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_clinical_en.md new file mode 100644 index 00000000000000..a0a9413550703a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_clinical_en.md @@ -0,0 +1,101 @@ +--- +layout: model +title: English Bert Embeddings model (from nlpie) +author: John Snow Labs +name: distilbert_embeddings_clinical +date: 2023-09-15 +tags: [open_source, distilbert, distilbert_embeddings, distilbertformaskedlm, en, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `clinical-distilbert` is a English model originally trained by `nlpie`. + +## Predicted Entities + + + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_clinical_en_5.1.2_3.0_1694771806781.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_clinical_en_5.1.2_3.0_1694771806781.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python +documentAssembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("document") + +tokenizer = Tokenizer() \ + .setInputCols("document") \ + .setOutputCol("token") + +embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_clinical","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("embeddings") \ + .setCaseSensitive(True) + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings]) + +data = spark.createDataFrame([["I love Spark-NLP"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val embeddings = DistilBertEmbeddings.pretrained("distilbert_embeddings_clinical","en") + .setInputCols(Array("document", "token")) + .setOutputCol("embeddings") + .setCaseSensitive(True) + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings)) + +val data = Seq("I love Spark-NLP").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_embeddings_clinical| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[sentence, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|243.6 MB| +|Case sensitive:|false| + +## References + +References + +https://huggingface.co/nlpie/clinical-distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_google_job_data_tuned_trial_8_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_google_job_data_tuned_trial_8_en.md new file mode 100644 index 00000000000000..1d3c9cefce2c49 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_google_job_data_tuned_trial_8_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_embeddings_google_job_data_tuned_trial_8 DistilBertEmbeddings from EslamAhmed +author: John Snow Labs +name: distilbert_embeddings_google_job_data_tuned_trial_8 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_embeddings_google_job_data_tuned_trial_8` is a English model originally trained by EslamAhmed. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_google_job_data_tuned_trial_8_en_5.1.2_3.0_1694773297076.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_google_job_data_tuned_trial_8_en_5.1.2_3.0_1694773297076.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_embeddings_google_job_data_tuned_trial_8","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_embeddings_google_job_data_tuned_trial_8", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_embeddings_google_job_data_tuned_trial_8| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|402.3 MB| + +## References + +https://huggingface.co/EslamAhmed/google_Job_data_tuned_trial_8_11-2-2022 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_we4lkd_aml_1921_2017_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_we4lkd_aml_1921_2017_en.md new file mode 100644 index 00000000000000..f869068d5dd6da --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_embeddings_we4lkd_aml_1921_2017_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_embeddings_we4lkd_aml_1921_2017 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: distilbert_embeddings_we4lkd_aml_1921_2017 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_embeddings_we4lkd_aml_1921_2017` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_we4lkd_aml_1921_2017_en_5.1.2_3.0_1694779750303.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_embeddings_we4lkd_aml_1921_2017_en_5.1.2_3.0_1694779750303.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_embeddings_we4lkd_aml_1921_2017","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_embeddings_we4lkd_aml_1921_2017", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_embeddings_we4lkd_aml_1921_2017| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2017 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_imdb_lyk0013_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_imdb_lyk0013_en.md new file mode 100644 index 00000000000000..0b85162c5f5726 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_imdb_lyk0013_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_finetuned_imdb_lyk0013 DistilBertEmbeddings from lyk0013 +author: John Snow Labs +name: distilbert_finetuned_imdb_lyk0013 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_finetuned_imdb_lyk0013` is a English model originally trained by lyk0013. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_finetuned_imdb_lyk0013_en_5.1.2_3.0_1694790297554.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_finetuned_imdb_lyk0013_en_5.1.2_3.0_1694790297554.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_finetuned_imdb_lyk0013","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_finetuned_imdb_lyk0013", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_finetuned_imdb_lyk0013| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/lyk0013/distilbert-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_imdb_tsabing_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_imdb_tsabing_en.md new file mode 100644 index 00000000000000..b35ecb267a931f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_imdb_tsabing_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_finetuned_imdb_tsabing DistilBertEmbeddings from Tsabing +author: John Snow Labs +name: distilbert_finetuned_imdb_tsabing +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_finetuned_imdb_tsabing` is a English model originally trained by Tsabing. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_finetuned_imdb_tsabing_en_5.1.2_3.0_1694789241169.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_finetuned_imdb_tsabing_en_5.1.2_3.0_1694789241169.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_finetuned_imdb_tsabing","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_finetuned_imdb_tsabing", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_finetuned_imdb_tsabing| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Tsabing/distilbert-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_spmlm_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_spmlm_en.md new file mode 100644 index 00000000000000..41b6b0a5006381 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_finetuned_spmlm_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_finetuned_spmlm DistilBertEmbeddings from ashwathjadhav23 +author: John Snow Labs +name: distilbert_finetuned_spmlm +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_finetuned_spmlm` is a English model originally trained by ashwathjadhav23. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_finetuned_spmlm_en_5.1.2_3.0_1694773887957.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_finetuned_spmlm_en_5.1.2_3.0_1694773887957.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_finetuned_spmlm","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_finetuned_spmlm", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_finetuned_spmlm| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|243.7 MB| + +## References + +https://huggingface.co/ashwathjadhav23/DistilBert_Finetuned_SpMLM \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_french_explorer_classification_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_french_explorer_classification_en.md new file mode 100644 index 00000000000000..5d13d4d3aeccb5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_french_explorer_classification_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_french_explorer_classification DistilBertEmbeddings from factored +author: John Snow Labs +name: distilbert_french_explorer_classification +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_french_explorer_classification` is a English model originally trained by factored. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_french_explorer_classification_en_5.1.2_3.0_1694779552028.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_french_explorer_classification_en_5.1.2_3.0_1694779552028.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_french_explorer_classification","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_french_explorer_classification", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_french_explorer_classification| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.1 MB| + +## References + +https://huggingface.co/factored/distilbert-fr-explorer-classification \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_hemingway_sar_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_hemingway_sar_en.md new file mode 100644 index 00000000000000..c6f43bb5523c7f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_hemingway_sar_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_hemingway_sar DistilBertEmbeddings from khazen2 +author: John Snow Labs +name: distilbert_hemingway_sar +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_hemingway_sar` is a English model originally trained by khazen2. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_hemingway_sar_en_5.1.2_3.0_1694786578751.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_hemingway_sar_en_5.1.2_3.0_1694786578751.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_hemingway_sar","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_hemingway_sar", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_hemingway_sar| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/khazen2/DistilBERT_Hemingway_SAR \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_hinglish_big_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_hinglish_big_en.md new file mode 100644 index 00000000000000..5b9789063aac23 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_hinglish_big_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_hinglish_big DistilBertEmbeddings from aditeyabaral +author: John Snow Labs +name: distilbert_hinglish_big +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_hinglish_big` is a English model originally trained by aditeyabaral. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_hinglish_big_en_5.1.2_3.0_1694779769717.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_hinglish_big_en_5.1.2_3.0_1694779769717.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_hinglish_big","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_hinglish_big", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_hinglish_big| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.0 MB| + +## References + +https://huggingface.co/aditeyabaral/distilbert-hinglish-big \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_hinglish_small_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_hinglish_small_en.md new file mode 100644 index 00000000000000..cb32a2ccc8ce17 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_hinglish_small_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_hinglish_small DistilBertEmbeddings from aditeyabaral +author: John Snow Labs +name: distilbert_hinglish_small +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_hinglish_small` is a English model originally trained by aditeyabaral. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_hinglish_small_en_5.1.2_3.0_1694779874373.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_hinglish_small_en_5.1.2_3.0_1694779874373.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_hinglish_small","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_hinglish_small", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_hinglish_small| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.0 MB| + +## References + +https://huggingface.co/aditeyabaral/distilbert-hinglish-small \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_imdb_negative_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_imdb_negative_en.md new file mode 100644 index 00000000000000..aa56d258ad77af --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_imdb_negative_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_imdb_negative DistilBertEmbeddings from michalwilk123 +author: John Snow Labs +name: distilbert_imdb_negative +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_imdb_negative` is a English model originally trained by michalwilk123. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_imdb_negative_en_5.1.2_3.0_1694782498235.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_imdb_negative_en_5.1.2_3.0_1694782498235.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_imdb_negative","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_imdb_negative", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_imdb_negative| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/michalwilk123/distilbert-imdb-negative \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_imdb_positive_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_imdb_positive_en.md new file mode 100644 index 00000000000000..ca0bd79a1b7f8d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_imdb_positive_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_imdb_positive DistilBertEmbeddings from michalwilk123 +author: John Snow Labs +name: distilbert_imdb_positive +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_imdb_positive` is a English model originally trained by michalwilk123. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_imdb_positive_en_5.1.2_3.0_1694782618191.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_imdb_positive_en_5.1.2_3.0_1694782618191.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_imdb_positive","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_imdb_positive", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_imdb_positive| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/michalwilk123/distilbert-imdb-positive \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_1000k_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_1000k_en.md new file mode 100644 index 00000000000000..c19330a9e22c6f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_1000k_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_mlm_1000k DistilBertEmbeddings from vocab-transformers +author: John Snow Labs +name: distilbert_mlm_1000k +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_mlm_1000k` is a English model originally trained by vocab-transformers. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_mlm_1000k_en_5.1.2_3.0_1694788526784.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_mlm_1000k_en_5.1.2_3.0_1694788526784.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_mlm_1000k","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_mlm_1000k", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_mlm_1000k| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|246.8 MB| + +## References + +https://huggingface.co/vocab-transformers/distilbert-mlm-1000k \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_250k_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_250k_en.md new file mode 100644 index 00000000000000..17506d9d98ca7d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_250k_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_mlm_250k DistilBertEmbeddings from vocab-transformers +author: John Snow Labs +name: distilbert_mlm_250k +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_mlm_250k` is a English model originally trained by vocab-transformers. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_mlm_250k_en_5.1.2_3.0_1694788223580.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_mlm_250k_en_5.1.2_3.0_1694788223580.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_mlm_250k","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_mlm_250k", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_mlm_250k| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.0 MB| + +## References + +https://huggingface.co/vocab-transformers/distilbert-mlm-250k \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_500k_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_500k_en.md new file mode 100644 index 00000000000000..09f5a95e3f3201 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_500k_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_mlm_500k DistilBertEmbeddings from vocab-transformers +author: John Snow Labs +name: distilbert_mlm_500k +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_mlm_500k` is a English model originally trained by vocab-transformers. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_mlm_500k_en_5.1.2_3.0_1694788324657.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_mlm_500k_en_5.1.2_3.0_1694788324657.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_mlm_500k","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_mlm_500k", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_mlm_500k| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|246.9 MB| + +## References + +https://huggingface.co/vocab-transformers/distilbert-mlm-500k \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_750k_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_750k_en.md new file mode 100644 index 00000000000000..dcc0f4d7c33da6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_750k_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_mlm_750k DistilBertEmbeddings from vocab-transformers +author: John Snow Labs +name: distilbert_mlm_750k +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_mlm_750k` is a English model originally trained by vocab-transformers. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_mlm_750k_en_5.1.2_3.0_1694788420155.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_mlm_750k_en_5.1.2_3.0_1694788420155.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_mlm_750k","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_mlm_750k", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_mlm_750k| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|246.8 MB| + +## References + +https://huggingface.co/vocab-transformers/distilbert-mlm-750k \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_best_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_best_en.md new file mode 100644 index 00000000000000..1eaec4ce82c3fa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_mlm_best_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_mlm_best DistilBertEmbeddings from vocab-transformers +author: John Snow Labs +name: distilbert_mlm_best +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_mlm_best` is a English model originally trained by vocab-transformers. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_mlm_best_en_5.1.2_3.0_1694788626661.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_mlm_best_en_5.1.2_3.0_1694788626661.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_mlm_best","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_mlm_best", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_mlm_best| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|246.9 MB| + +## References + +https://huggingface.co/vocab-transformers/distilbert-mlm-best \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_perigon_200k_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_perigon_200k_en.md new file mode 100644 index 00000000000000..6fcc0bad67de51 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_perigon_200k_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_perigon_200k DistilBertEmbeddings from judy93536 +author: John Snow Labs +name: distilbert_perigon_200k +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_perigon_200k` is a English model originally trained by judy93536. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_perigon_200k_en_5.1.2_3.0_1694785838237.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_perigon_200k_en_5.1.2_3.0_1694785838237.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_perigon_200k","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_perigon_200k", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_perigon_200k| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/judy93536/distilbert-perigon-200k \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_pubmed_mlm_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_pubmed_mlm_en.md new file mode 100644 index 00000000000000..9b38b3d88bb013 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_pubmed_mlm_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_pubmed_mlm DistilBertEmbeddings from Gaborandi +author: John Snow Labs +name: distilbert_pubmed_mlm +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_pubmed_mlm` is a English model originally trained by Gaborandi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_pubmed_mlm_en_5.1.2_3.0_1694775368835.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_pubmed_mlm_en_5.1.2_3.0_1694775368835.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_pubmed_mlm","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_pubmed_mlm", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_pubmed_mlm| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/Gaborandi/distilbert-pubmed-MLM \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_ravenk_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_ravenk_en.md new file mode 100644 index 00000000000000..2db4d812e44890 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_ravenk_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_ravenk DistilBertEmbeddings from RavenK +author: John Snow Labs +name: distilbert_ravenk +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_ravenk` is a English model originally trained by RavenK. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_ravenk_en_5.1.2_3.0_1694786300721.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_ravenk_en_5.1.2_3.0_1694786300721.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_ravenk","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_ravenk", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_ravenk| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/RavenK/distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_sparsembed_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_sparsembed_en.md new file mode 100644 index 00000000000000..a7991ca7e186ab --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_sparsembed_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_sparsembed DistilBertEmbeddings from raphaelsty +author: John Snow Labs +name: distilbert_sparsembed +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_sparsembed` is a English model originally trained by raphaelsty. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_sparsembed_en_5.1.2_3.0_1694787885018.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_sparsembed_en_5.1.2_3.0_1694787885018.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_sparsembed","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_sparsembed", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_sparsembed| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/raphaelsty/distilbert-sparsembed \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_splade_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_splade_en.md new file mode 100644 index 00000000000000..938bd19e5035ad --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_splade_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_splade DistilBertEmbeddings from raphaelsty +author: John Snow Labs +name: distilbert_splade +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_splade` is a English model originally trained by raphaelsty. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_splade_en_5.1.2_3.0_1694787786344.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_splade_en_5.1.2_3.0_1694787786344.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_splade","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_splade", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_splade| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/raphaelsty/distilbert-splade \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_ugiugi_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_ugiugi_en.md new file mode 100644 index 00000000000000..4ca0440e6b3c1c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_ugiugi_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distilbert_ugiugi DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: distilbert_ugiugi +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distilbert_ugiugi` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_ugiugi_en_5.1.2_3.0_1694785503613.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_ugiugi_en_5.1.2_3.0_1694785503613.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distilbert_ugiugi","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distilbert_ugiugi", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distilbert_ugiugi| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/ugiugi/distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distilbert_v1_en.md b/docs/_posts/ahmedlone127/2023-09-15-distilbert_v1_en.md index 661174247fb785..53d82d34f6bb8c 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distilbert_v1_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distilbert_v1_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_v1_en_5.1.2_3.0_1694736931572.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_v1_en_5.1.2_3.0_1694736931572.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distilbert_v1_en_5.1.2_3.0_1694770244017.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distilbert_v1_en_5.1.2_3.0_1694770244017.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-distill_test_en.md b/docs/_posts/ahmedlone127/2023-09-15-distill_test_en.md new file mode 100644 index 00000000000000..b02c7b84a03c88 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distill_test_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distill_test DistilBertEmbeddings from domenicrosati +author: John Snow Labs +name: distill_test +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distill_test` is a English model originally trained by domenicrosati. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distill_test_en_5.1.2_3.0_1694778046009.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distill_test_en_5.1.2_3.0_1694778046009.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distill_test","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distill_test", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distill_test| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/domenicrosati/distill-test \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distillbert_base_spanish_uncased_finetuned_imdb_en.md b/docs/_posts/ahmedlone127/2023-09-15-distillbert_base_spanish_uncased_finetuned_imdb_en.md new file mode 100644 index 00000000000000..67a6ad4c4cac72 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-distillbert_base_spanish_uncased_finetuned_imdb_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English distillbert_base_spanish_uncased_finetuned_imdb DistilBertEmbeddings from franfram +author: John Snow Labs +name: distillbert_base_spanish_uncased_finetuned_imdb +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`distillbert_base_spanish_uncased_finetuned_imdb` is a English model originally trained by franfram. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distillbert_base_spanish_uncased_finetuned_imdb_en_5.1.2_3.0_1694790663206.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distillbert_base_spanish_uncased_finetuned_imdb_en_5.1.2_3.0_1694790663206.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("distillbert_base_spanish_uncased_finetuned_imdb","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("distillbert_base_spanish_uncased_finetuned_imdb", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|distillbert_base_spanish_uncased_finetuned_imdb| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|250.2 MB| + +## References + +https://huggingface.co/franfram/distillbert-base-spanish-uncased-finetuned-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-distillbert_base_spanish_uncased_finetuned_spanish_corpus_en.md b/docs/_posts/ahmedlone127/2023-09-15-distillbert_base_spanish_uncased_finetuned_spanish_corpus_en.md index 29817fb96f563c..52ed7660530b68 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-distillbert_base_spanish_uncased_finetuned_spanish_corpus_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-distillbert_base_spanish_uncased_finetuned_spanish_corpus_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distillbert_base_spanish_uncased_finetuned_spanish_corpus_en_5.1.2_3.0_1694736667906.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distillbert_base_spanish_uncased_finetuned_spanish_corpus_en_5.1.2_3.0_1694736667906.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/distillbert_base_spanish_uncased_finetuned_spanish_corpus_en_5.1.2_3.0_1694769979577.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/distillbert_base_spanish_uncased_finetuned_spanish_corpus_en_5.1.2_3.0_1694769979577.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-domain_adapted_arbert_goudma_en.md b/docs/_posts/ahmedlone127/2023-09-15-domain_adapted_arbert_goudma_en.md new file mode 100644 index 00000000000000..6f85457b85df97 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-domain_adapted_arbert_goudma_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English domain_adapted_arbert_goudma DistilBertEmbeddings from YassineToughrai +author: John Snow Labs +name: domain_adapted_arbert_goudma +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`domain_adapted_arbert_goudma` is a English model originally trained by YassineToughrai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/domain_adapted_arbert_goudma_en_5.1.2_3.0_1694782061367.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/domain_adapted_arbert_goudma_en_5.1.2_3.0_1694782061367.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("domain_adapted_arbert_goudma","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("domain_adapted_arbert_goudma", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|domain_adapted_arbert_goudma| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|606.8 MB| + +## References + +https://huggingface.co/YassineToughrai/Domain_adapted_ARBERT_GOUDMA \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-dummy_model_en.md b/docs/_posts/ahmedlone127/2023-09-15-dummy_model_en.md new file mode 100644 index 00000000000000..637b335a6645ef --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-dummy_model_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English dummy_model DistilBertEmbeddings from luoweijie +author: John Snow Labs +name: dummy_model +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`dummy_model` is a English model originally trained by luoweijie. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/dummy_model_en_5.1.2_3.0_1694781796190.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/dummy_model_en_5.1.2_3.0_1694781796190.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("dummy_model","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("dummy_model", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|dummy_model| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/luoweijie/dummy-model \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-e4a_covid_distilbert_base_romanian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-e4a_covid_distilbert_base_romanian_cased_en.md new file mode 100644 index 00000000000000..03a4e43ee86fcb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-e4a_covid_distilbert_base_romanian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English e4a_covid_distilbert_base_romanian_cased DistilBertEmbeddings from racai +author: John Snow Labs +name: e4a_covid_distilbert_base_romanian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`e4a_covid_distilbert_base_romanian_cased` is a English model originally trained by racai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/e4a_covid_distilbert_base_romanian_cased_en_5.1.2_3.0_1694786227826.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/e4a_covid_distilbert_base_romanian_cased_en_5.1.2_3.0_1694786227826.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("e4a_covid_distilbert_base_romanian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("e4a_covid_distilbert_base_romanian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|e4a_covid_distilbert_base_romanian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|305.9 MB| + +## References + +https://huggingface.co/racai/e4a-covid-distilbert-base-romanian-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-e4a_permits_distilbert_base_romanian_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-e4a_permits_distilbert_base_romanian_cased_en.md new file mode 100644 index 00000000000000..f223499ccfa25d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-e4a_permits_distilbert_base_romanian_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English e4a_permits_distilbert_base_romanian_cased DistilBertEmbeddings from racai +author: John Snow Labs +name: e4a_permits_distilbert_base_romanian_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`e4a_permits_distilbert_base_romanian_cased` is a English model originally trained by racai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/e4a_permits_distilbert_base_romanian_cased_en_5.1.2_3.0_1694786350915.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/e4a_permits_distilbert_base_romanian_cased_en_5.1.2_3.0_1694786350915.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("e4a_permits_distilbert_base_romanian_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("e4a_permits_distilbert_base_romanian_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|e4a_permits_distilbert_base_romanian_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|305.9 MB| + +## References + +https://huggingface.co/racai/e4a-permits-distilbert-base-romanian-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_v_large_doc_en.md b/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_v_large_doc_en.md new file mode 100644 index 00000000000000..477278a7117682 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_v_large_doc_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English efficient_splade_v_large_doc DistilBertEmbeddings from naver +author: John Snow Labs +name: efficient_splade_v_large_doc +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`efficient_splade_v_large_doc` is a English model originally trained by naver. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/efficient_splade_v_large_doc_en_5.1.2_3.0_1694778590163.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/efficient_splade_v_large_doc_en_5.1.2_3.0_1694778590163.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("efficient_splade_v_large_doc","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("efficient_splade_v_large_doc", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|efficient_splade_v_large_doc| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/naver/efficient-splade-V-large-doc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_v_large_query_en.md b/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_v_large_query_en.md new file mode 100644 index 00000000000000..bfc881dd2f0211 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_v_large_query_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English efficient_splade_v_large_query DistilBertEmbeddings from naver +author: John Snow Labs +name: efficient_splade_v_large_query +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`efficient_splade_v_large_query` is a English model originally trained by naver. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/efficient_splade_v_large_query_en_5.1.2_3.0_1694778680533.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/efficient_splade_v_large_query_en_5.1.2_3.0_1694778680533.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("efficient_splade_v_large_query","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("efficient_splade_v_large_query", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|efficient_splade_v_large_query| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.4 MB| + +## References + +https://huggingface.co/naver/efficient-splade-V-large-query \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_vi_bt_large_doc_en.md b/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_vi_bt_large_doc_en.md new file mode 100644 index 00000000000000..12c67a2c71b8d5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-efficient_splade_vi_bt_large_doc_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English efficient_splade_vi_bt_large_doc DistilBertEmbeddings from naver +author: John Snow Labs +name: efficient_splade_vi_bt_large_doc +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`efficient_splade_vi_bt_large_doc` is a English model originally trained by naver. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/efficient_splade_vi_bt_large_doc_en_5.1.2_3.0_1694778781866.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/efficient_splade_vi_bt_large_doc_en_5.1.2_3.0_1694778781866.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("efficient_splade_vi_bt_large_doc","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("efficient_splade_vi_bt_large_doc", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|efficient_splade_vi_bt_large_doc| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/naver/efficient-splade-VI-BT-large-doc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-eighteenth_century_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-eighteenth_century_distilbert_en.md new file mode 100644 index 00000000000000..28896709b6a7aa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-eighteenth_century_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English eighteenth_century_distilbert DistilBertEmbeddings from davanstrien +author: John Snow Labs +name: eighteenth_century_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`eighteenth_century_distilbert` is a English model originally trained by davanstrien. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/eighteenth_century_distilbert_en_5.1.2_3.0_1694780486021.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/eighteenth_century_distilbert_en_5.1.2_3.0_1694780486021.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("eighteenth_century_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("eighteenth_century_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|eighteenth_century_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|244.4 MB| + +## References + +https://huggingface.co/davanstrien/eighteenth-century-distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-erwt_year_en.md b/docs/_posts/ahmedlone127/2023-09-15-erwt_year_en.md new file mode 100644 index 00000000000000..3c4d09ca41735d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-erwt_year_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English erwt_year DistilBertEmbeddings from Livingwithmachines +author: John Snow Labs +name: erwt_year +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`erwt_year` is a English model originally trained by Livingwithmachines. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/erwt_year_en_5.1.2_3.0_1694780244581.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/erwt_year_en_5.1.2_3.0_1694780244581.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("erwt_year","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("erwt_year", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|erwt_year| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Livingwithmachines/erwt-year \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-erwt_year_masked_25_en.md b/docs/_posts/ahmedlone127/2023-09-15-erwt_year_masked_25_en.md new file mode 100644 index 00000000000000..06371f700c903b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-erwt_year_masked_25_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English erwt_year_masked_25 DistilBertEmbeddings from Livingwithmachines +author: John Snow Labs +name: erwt_year_masked_25 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`erwt_year_masked_25` is a English model originally trained by Livingwithmachines. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/erwt_year_masked_25_en_5.1.2_3.0_1694780473232.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/erwt_year_masked_25_en_5.1.2_3.0_1694780473232.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("erwt_year_masked_25","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("erwt_year_masked_25", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|erwt_year_masked_25| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Livingwithmachines/erwt-year-masked-25 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-erwt_year_masked_75_en.md b/docs/_posts/ahmedlone127/2023-09-15-erwt_year_masked_75_en.md new file mode 100644 index 00000000000000..8c8bc839960829 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-erwt_year_masked_75_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English erwt_year_masked_75 DistilBertEmbeddings from Livingwithmachines +author: John Snow Labs +name: erwt_year_masked_75 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`erwt_year_masked_75` is a English model originally trained by Livingwithmachines. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/erwt_year_masked_75_en_5.1.2_3.0_1694780617608.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/erwt_year_masked_75_en_5.1.2_3.0_1694780617608.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("erwt_year_masked_75","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("erwt_year_masked_75", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|erwt_year_masked_75| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Livingwithmachines/erwt-year-masked-75 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-erwt_year_southern_sotho_en.md b/docs/_posts/ahmedlone127/2023-09-15-erwt_year_southern_sotho_en.md new file mode 100644 index 00000000000000..bf355fe105aac2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-erwt_year_southern_sotho_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English erwt_year_southern_sotho DistilBertEmbeddings from Livingwithmachines +author: John Snow Labs +name: erwt_year_southern_sotho +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`erwt_year_southern_sotho` is a English model originally trained by Livingwithmachines. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/erwt_year_southern_sotho_en_5.1.2_3.0_1694780351987.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/erwt_year_southern_sotho_en_5.1.2_3.0_1694780351987.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("erwt_year_southern_sotho","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("erwt_year_southern_sotho", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|erwt_year_southern_sotho| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.4 MB| + +## References + +https://huggingface.co/Livingwithmachines/erwt-year-st \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-experiment_en.md b/docs/_posts/ahmedlone127/2023-09-15-experiment_en.md new file mode 100644 index 00000000000000..b8c55b9fd506fa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-experiment_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English experiment DistilBertEmbeddings from apl33 +author: John Snow Labs +name: experiment +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`experiment` is a English model originally trained by apl33. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/experiment_en_5.1.2_3.0_1694779805982.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/experiment_en_5.1.2_3.0_1694779805982.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("experiment","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("experiment", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|experiment| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|402.3 MB| + +## References + +https://huggingface.co/apl33/experiment \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-few_mask_en.md b/docs/_posts/ahmedlone127/2023-09-15-few_mask_en.md new file mode 100644 index 00000000000000..ce492ff554f657 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-few_mask_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English few_mask DistilBertEmbeddings from Ondiet +author: John Snow Labs +name: few_mask +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`few_mask` is a English model originally trained by Ondiet. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/few_mask_en_5.1.2_3.0_1694788941452.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/few_mask_en_5.1.2_3.0_1694788941452.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("few_mask","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("few_mask", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|few_mask| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Ondiet/few_mask \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-film20000distilbert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-film20000distilbert_base_uncased_en.md index 74d1ca7c856994..8cc80dd7d0cead 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-film20000distilbert_base_uncased_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-film20000distilbert_base_uncased_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/film20000distilbert_base_uncased_en_5.1.2_3.0_1694736242255.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/film20000distilbert_base_uncased_en_5.1.2_3.0_1694736242255.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/film20000distilbert_base_uncased_en_5.1.2_3.0_1694774514582.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/film20000distilbert_base_uncased_en_5.1.2_3.0_1694774514582.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-film20000film20000distilbert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-film20000film20000distilbert_base_uncased_en.md new file mode 100644 index 00000000000000..cae359671ffaae --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-film20000film20000distilbert_base_uncased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English film20000film20000distilbert_base_uncased DistilBertEmbeddings from AmaiaSolaun +author: John Snow Labs +name: film20000film20000distilbert_base_uncased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`film20000film20000distilbert_base_uncased` is a English model originally trained by AmaiaSolaun. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/film20000film20000distilbert_base_uncased_en_5.1.2_3.0_1694775693003.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/film20000film20000distilbert_base_uncased_en_5.1.2_3.0_1694775693003.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("film20000film20000distilbert_base_uncased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("film20000film20000distilbert_base_uncased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|film20000film20000distilbert_base_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/AmaiaSolaun/film20000film20000distilbert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-film95000distilbert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-film95000distilbert_base_uncased_en.md new file mode 100644 index 00000000000000..1a617a1bdd3510 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-film95000distilbert_base_uncased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English film95000distilbert_base_uncased DistilBertEmbeddings from AmaiaSolaun +author: John Snow Labs +name: film95000distilbert_base_uncased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`film95000distilbert_base_uncased` is a English model originally trained by AmaiaSolaun. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/film95000distilbert_base_uncased_en_5.1.2_3.0_1694776512015.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/film95000distilbert_base_uncased_en_5.1.2_3.0_1694776512015.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("film95000distilbert_base_uncased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("film95000distilbert_base_uncased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|film95000distilbert_base_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/AmaiaSolaun/film95000distilbert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-film98984distilbert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-film98984distilbert_base_uncased_en.md new file mode 100644 index 00000000000000..2d5bbcbe0fd425 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-film98984distilbert_base_uncased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English film98984distilbert_base_uncased DistilBertEmbeddings from AmaiaSolaun +author: John Snow Labs +name: film98984distilbert_base_uncased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`film98984distilbert_base_uncased` is a English model originally trained by AmaiaSolaun. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/film98984distilbert_base_uncased_en_5.1.2_3.0_1694775585695.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/film98984distilbert_base_uncased_en_5.1.2_3.0_1694775585695.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("film98984distilbert_base_uncased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("film98984distilbert_base_uncased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|film98984distilbert_base_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/AmaiaSolaun/film98984distilbert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-fine_tuned_distilbert_nosql_injection_en.md b/docs/_posts/ahmedlone127/2023-09-15-fine_tuned_distilbert_nosql_injection_en.md new file mode 100644 index 00000000000000..4f609c5a04c68a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-fine_tuned_distilbert_nosql_injection_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English fine_tuned_distilbert_nosql_injection DistilBertEmbeddings from ankush-003 +author: John Snow Labs +name: fine_tuned_distilbert_nosql_injection +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_distilbert_nosql_injection` is a English model originally trained by ankush-003. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_distilbert_nosql_injection_en_5.1.2_3.0_1694775832410.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_distilbert_nosql_injection_en_5.1.2_3.0_1694775832410.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("fine_tuned_distilbert_nosql_injection","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("fine_tuned_distilbert_nosql_injection", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_distilbert_nosql_injection| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/ankush-003/fine-tuned-distilbert-nosql-injection \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-first_try_4_en.md b/docs/_posts/ahmedlone127/2023-09-15-first_try_4_en.md new file mode 100644 index 00000000000000..a26be8582a30fa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-first_try_4_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English first_try_4 DistilBertEmbeddings from disanda +author: John Snow Labs +name: first_try_4 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`first_try_4` is a English model originally trained by disanda. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/first_try_4_en_5.1.2_3.0_1694773416430.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/first_try_4_en_5.1.2_3.0_1694773416430.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("first_try_4","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("first_try_4", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|first_try_4| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/disanda/first_try_4 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-flang_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-flang_distilbert_en.md new file mode 100644 index 00000000000000..f6ef0f490e70cf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-flang_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English flang_distilbert DistilBertEmbeddings from SALT-NLP +author: John Snow Labs +name: flang_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`flang_distilbert` is a English model originally trained by SALT-NLP. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/flang_distilbert_en_5.1.2_3.0_1694777676228.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/flang_distilbert_en_5.1.2_3.0_1694777676228.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("flang_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("flang_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|flang_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/SALT-NLP/FLANG-DistilBERT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-german_poetry_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-german_poetry_distilbert_en.md new file mode 100644 index 00000000000000..8d51fc0905638c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-german_poetry_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English german_poetry_distilbert DistilBertEmbeddings from Anjoe +author: John Snow Labs +name: german_poetry_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`german_poetry_distilbert` is a English model originally trained by Anjoe. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/german_poetry_distilbert_en_5.1.2_3.0_1694774320800.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/german_poetry_distilbert_en_5.1.2_3.0_1694774320800.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("german_poetry_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("german_poetry_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|german_poetry_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|250.3 MB| + +## References + +https://huggingface.co/Anjoe/german-poetry-distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-google_job_data_tuned_trial_1_en.md b/docs/_posts/ahmedlone127/2023-09-15-google_job_data_tuned_trial_1_en.md new file mode 100644 index 00000000000000..6a6806eaa9bf20 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-google_job_data_tuned_trial_1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English google_job_data_tuned_trial_1 DistilBertEmbeddings from EslamAhmed +author: John Snow Labs +name: google_job_data_tuned_trial_1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`google_job_data_tuned_trial_1` is a English model originally trained by EslamAhmed. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/google_job_data_tuned_trial_1_en_5.1.2_3.0_1694770671424.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/google_job_data_tuned_trial_1_en_5.1.2_3.0_1694770671424.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("google_job_data_tuned_trial_1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("google_job_data_tuned_trial_1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|google_job_data_tuned_trial_1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|402.3 MB| + +## References + +https://huggingface.co/EslamAhmed/google_Job_data_tuned_trial_1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-google_job_data_tuned_trial_2_11_2_2022_en.md b/docs/_posts/ahmedlone127/2023-09-15-google_job_data_tuned_trial_2_11_2_2022_en.md new file mode 100644 index 00000000000000..09bd2241a5d469 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-google_job_data_tuned_trial_2_11_2_2022_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English google_job_data_tuned_trial_2_11_2_2022 DistilBertEmbeddings from EslamAhmed +author: John Snow Labs +name: google_job_data_tuned_trial_2_11_2_2022 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`google_job_data_tuned_trial_2_11_2_2022` is a English model originally trained by EslamAhmed. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/google_job_data_tuned_trial_2_11_2_2022_en_5.1.2_3.0_1694772782812.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/google_job_data_tuned_trial_2_11_2_2022_en_5.1.2_3.0_1694772782812.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("google_job_data_tuned_trial_2_11_2_2022","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("google_job_data_tuned_trial_2_11_2_2022", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|google_job_data_tuned_trial_2_11_2_2022| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|402.3 MB| + +## References + +https://huggingface.co/EslamAhmed/google_Job_data_tuned_trial_2_11-2-2022 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_cosine_en.md b/docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_cosine_en.md index f1b4ae3231f99c..321a26b9575858 100644 --- a/docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_cosine_en.md +++ b/docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_cosine_en.md @@ -24,8 +24,8 @@ Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to {:.btn-box} -[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/hf_distilbert_imdb_mlm_cosine_en_5.1.2_3.0_1694736657876.zip){:.button.button-orange.button-orange-trans.arr.button-icon} -[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/hf_distilbert_imdb_mlm_cosine_en_5.1.2_3.0_1694736657876.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/hf_distilbert_imdb_mlm_cosine_en_5.1.2_3.0_1694769976827.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/hf_distilbert_imdb_mlm_cosine_en_5.1.2_3.0_1694769976827.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} ## How to use diff --git a/docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_en.md b/docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_en.md new file mode 100644 index 00000000000000..598fef3dfcef95 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-hf_distilbert_imdb_mlm_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English hf_distilbert_imdb_mlm DistilBertEmbeddings from nos1de +author: John Snow Labs +name: hf_distilbert_imdb_mlm +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`hf_distilbert_imdb_mlm` is a English model originally trained by nos1de. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/hf_distilbert_imdb_mlm_en_5.1.2_3.0_1694791148509.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/hf_distilbert_imdb_mlm_en_5.1.2_3.0_1694791148509.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("hf_distilbert_imdb_mlm","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("hf_distilbert_imdb_mlm", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|hf_distilbert_imdb_mlm| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/nos1de/hf-distilbert-imdb-mlm \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-hinglish_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-hinglish_distilbert_en.md new file mode 100644 index 00000000000000..c571c046c03da8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-hinglish_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English hinglish_distilbert DistilBertEmbeddings from meghanabhange +author: John Snow Labs +name: hinglish_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`hinglish_distilbert` is a English model originally trained by meghanabhange. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/hinglish_distilbert_en_5.1.2_3.0_1694782372500.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/hinglish_distilbert_en_5.1.2_3.0_1694782372500.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("hinglish_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("hinglish_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|hinglish_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|243.7 MB| + +## References + +https://huggingface.co/meghanabhange/Hinglish-DistilBert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-indic_transformers_hindi_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-indic_transformers_hindi_distilbert_en.md new file mode 100644 index 00000000000000..ae1d2a7f6cb8bc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-indic_transformers_hindi_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English indic_transformers_hindi_distilbert DistilBertEmbeddings from neuralspace +author: John Snow Labs +name: indic_transformers_hindi_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`indic_transformers_hindi_distilbert` is a English model originally trained by neuralspace. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/indic_transformers_hindi_distilbert_en_5.1.2_3.0_1694783192541.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/indic_transformers_hindi_distilbert_en_5.1.2_3.0_1694783192541.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("indic_transformers_hindi_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("indic_transformers_hindi_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|indic_transformers_hindi_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/neuralspace/indic-transformers-hi-distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adagrad_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adagrad_en.md new file mode 100644 index 00000000000000..324774f9db35d9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adagrad_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_distilbert_mlm_adagrad DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_distilbert_mlm_adagrad +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_distilbert_mlm_adagrad` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adagrad_en_5.1.2_3.0_1694788039538.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adagrad_en_5.1.2_3.0_1694788039538.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_distilbert_mlm_adagrad","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_distilbert_mlm_adagrad", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_distilbert_mlm_adagrad| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-DistilBERT-mlm-adagrad \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_hf_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_hf_en.md new file mode 100644 index 00000000000000..d36fb1f1702e99 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_hf_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_distilbert_mlm_adamw_hf DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_distilbert_mlm_adamw_hf +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_distilbert_mlm_adamw_hf` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adamw_hf_en_5.1.2_3.0_1694787638535.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adamw_hf_en_5.1.2_3.0_1694787638535.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_distilbert_mlm_adamw_hf","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_distilbert_mlm_adamw_hf", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_distilbert_mlm_adamw_hf| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-DistilBERT-mlm-adamw_hf \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_0608_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_0608_en.md new file mode 100644 index 00000000000000..6f7fa1991c81dd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_0608_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_distilbert_mlm_adamw_torch_0608 DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_distilbert_mlm_adamw_torch_0608 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_distilbert_mlm_adamw_torch_0608` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adamw_torch_0608_en_5.1.2_3.0_1694788142265.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adamw_torch_0608_en_5.1.2_3.0_1694788142265.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_distilbert_mlm_adamw_torch_0608","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_distilbert_mlm_adamw_torch_0608", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_distilbert_mlm_adamw_torch_0608| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.7 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-DistilBERT-mlm-adamw_torch_0608 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_en.md new file mode 100644 index 00000000000000..c93842c9710865 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_distilbert_mlm_adamw_torch DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_distilbert_mlm_adamw_torch +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_distilbert_mlm_adamw_torch` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adamw_torch_en_5.1.2_3.0_1694787825797.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adamw_torch_en_5.1.2_3.0_1694787825797.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_distilbert_mlm_adamw_torch","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_distilbert_mlm_adamw_torch", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_distilbert_mlm_adamw_torch| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-DistilBERT-mlm-adamw_torch \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_fused_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_fused_en.md new file mode 100644 index 00000000000000..1063741d4d1b59 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_adamw_torch_fused_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_distilbert_mlm_adamw_torch_fused DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_distilbert_mlm_adamw_torch_fused +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_distilbert_mlm_adamw_torch_fused` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adamw_torch_fused_en_5.1.2_3.0_1694788244866.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_adamw_torch_fused_en_5.1.2_3.0_1694788244866.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_distilbert_mlm_adamw_torch_fused","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_distilbert_mlm_adamw_torch_fused", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_distilbert_mlm_adamw_torch_fused| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-DistilBERT-mlm-adamw_torch_fused \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_lion_32bit_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_lion_32bit_en.md new file mode 100644 index 00000000000000..776b5189ddfcba --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_lion_32bit_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_distilbert_mlm_lion_32bit DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_distilbert_mlm_lion_32bit +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_distilbert_mlm_lion_32bit` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_lion_32bit_en_5.1.2_3.0_1694788344252.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_lion_32bit_en_5.1.2_3.0_1694788344252.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_distilbert_mlm_lion_32bit","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_distilbert_mlm_lion_32bit", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_distilbert_mlm_lion_32bit| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|245.9 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-DistilBERT-mlm-lion_32bit \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_lion_32bit_test_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_lion_32bit_test_en.md new file mode 100644 index 00000000000000..0672005b36e2aa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_lion_32bit_test_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_distilbert_mlm_lion_32bit_test DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_distilbert_mlm_lion_32bit_test +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_distilbert_mlm_lion_32bit_test` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_lion_32bit_test_en_5.1.2_3.0_1694788450083.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_lion_32bit_test_en_5.1.2_3.0_1694788450083.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_distilbert_mlm_lion_32bit_test","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_distilbert_mlm_lion_32bit_test", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_distilbert_mlm_lion_32bit_test| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|245.9 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-DistilBERT-mlm-lion_32bit_test \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_sgd_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_sgd_en.md new file mode 100644 index 00000000000000..c1dee01844e52a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_distilbert_mlm_sgd_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_distilbert_mlm_sgd DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_distilbert_mlm_sgd +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_distilbert_mlm_sgd` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_sgd_en_5.1.2_3.0_1694787934386.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_distilbert_mlm_sgd_en_5.1.2_3.0_1694787934386.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_distilbert_mlm_sgd","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_distilbert_mlm_sgd", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_distilbert_mlm_sgd| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-DistilBERT-mlm-sgd \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-inisw08_robert_mlm_adamw_torch_test_en.md b/docs/_posts/ahmedlone127/2023-09-15-inisw08_robert_mlm_adamw_torch_test_en.md new file mode 100644 index 00000000000000..dfff7490abf030 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-inisw08_robert_mlm_adamw_torch_test_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English inisw08_robert_mlm_adamw_torch_test DistilBertEmbeddings from ugiugi +author: John Snow Labs +name: inisw08_robert_mlm_adamw_torch_test +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`inisw08_robert_mlm_adamw_torch_test` is a English model originally trained by ugiugi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/inisw08_robert_mlm_adamw_torch_test_en_5.1.2_3.0_1694789322009.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/inisw08_robert_mlm_adamw_torch_test_en_5.1.2_3.0_1694789322009.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("inisw08_robert_mlm_adamw_torch_test","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("inisw08_robert_mlm_adamw_torch_test", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|inisw08_robert_mlm_adamw_torch_test| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/ugiugi/inisw08-RoBERT-mlm-adamw_torch_test \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-javanese_distilbert_small_imdb_jv.md b/docs/_posts/ahmedlone127/2023-09-15-javanese_distilbert_small_imdb_jv.md new file mode 100644 index 00000000000000..7954b2cb6667a5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-javanese_distilbert_small_imdb_jv.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Javanese javanese_distilbert_small_imdb DistilBertEmbeddings from w11wo +author: John Snow Labs +name: javanese_distilbert_small_imdb +date: 2023-09-15 +tags: [distilbert, jv, open_source, fill_mask, onnx] +task: Embeddings +language: jv +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`javanese_distilbert_small_imdb` is a Javanese model originally trained by w11wo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/javanese_distilbert_small_imdb_jv_5.1.2_3.0_1694785464605.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/javanese_distilbert_small_imdb_jv_5.1.2_3.0_1694785464605.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("javanese_distilbert_small_imdb","jv") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("javanese_distilbert_small_imdb", "jv") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|javanese_distilbert_small_imdb| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|jv| +|Size:|247.6 MB| + +## References + +https://huggingface.co/w11wo/javanese-distilbert-small-imdb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-javanese_distilbert_small_jv.md b/docs/_posts/ahmedlone127/2023-09-15-javanese_distilbert_small_jv.md new file mode 100644 index 00000000000000..3374867b783e48 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-javanese_distilbert_small_jv.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Javanese javanese_distilbert_small DistilBertEmbeddings from w11wo +author: John Snow Labs +name: javanese_distilbert_small +date: 2023-09-15 +tags: [distilbert, jv, open_source, fill_mask, onnx] +task: Embeddings +language: jv +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`javanese_distilbert_small` is a Javanese model originally trained by w11wo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/javanese_distilbert_small_jv_5.1.2_3.0_1694785574408.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/javanese_distilbert_small_jv_5.1.2_3.0_1694785574408.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("javanese_distilbert_small","jv") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("javanese_distilbert_small", "jv") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|javanese_distilbert_small| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|jv| +|Size:|247.6 MB| + +## References + +https://huggingface.co/w11wo/javanese-distilbert-small \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_full_corpus_10.0_en.md b/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_full_corpus_10.0_en.md new file mode 100644 index 00000000000000..16a4bef397b6e4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_full_corpus_10.0_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English kaz_legal_distilbert_full_corpus_10.0 DistilBertEmbeddings from kaisar-barlybay-sse +author: John Snow Labs +name: kaz_legal_distilbert_full_corpus_10.0 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`kaz_legal_distilbert_full_corpus_10.0` is a English model originally trained by kaisar-barlybay-sse. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/kaz_legal_distilbert_full_corpus_10.0_en_5.1.2_3.0_1694781030169.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/kaz_legal_distilbert_full_corpus_10.0_en_5.1.2_3.0_1694781030169.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("kaz_legal_distilbert_full_corpus_10.0","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("kaz_legal_distilbert_full_corpus_10.0", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|kaz_legal_distilbert_full_corpus_10.0| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/kaisar-barlybay-sse/kaz_legal_distilbert_full_corpus_10.0 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_full_corpus_3.0_en.md b/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_full_corpus_3.0_en.md new file mode 100644 index 00000000000000..316e5e5bcf3328 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_full_corpus_3.0_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English kaz_legal_distilbert_full_corpus_3.0 DistilBertEmbeddings from kaisar-barlybay-sse +author: John Snow Labs +name: kaz_legal_distilbert_full_corpus_3.0 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`kaz_legal_distilbert_full_corpus_3.0` is a English model originally trained by kaisar-barlybay-sse. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/kaz_legal_distilbert_full_corpus_3.0_en_5.1.2_3.0_1694780769803.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/kaz_legal_distilbert_full_corpus_3.0_en_5.1.2_3.0_1694780769803.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("kaz_legal_distilbert_full_corpus_3.0","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("kaz_legal_distilbert_full_corpus_3.0", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|kaz_legal_distilbert_full_corpus_3.0| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/kaisar-barlybay-sse/kaz_legal_distilbert_full_corpus_3.0 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545_en.md b/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545_en.md new file mode 100644 index 00000000000000..7bd19e82e8bdf7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545 DistilBertEmbeddings from kaisar-barlybay-sse +author: John Snow Labs +name: kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545` is a English model originally trained by kaisar-barlybay-sse. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545_en_5.1.2_3.0_1694782306602.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545_en_5.1.2_3.0_1694782306602.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.0 MB| + +## References + +https://huggingface.co/kaisar-barlybay-sse/kaz_legal_distilbert_legal_corpus_312818008_words_4.945454545454545 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-lsg_distilbert_base_uncased_4096_en.md b/docs/_posts/ahmedlone127/2023-09-15-lsg_distilbert_base_uncased_4096_en.md new file mode 100644 index 00000000000000..376789eb00edb9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-lsg_distilbert_base_uncased_4096_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English lsg_distilbert_base_uncased_4096 DistilBertEmbeddings from ccdv +author: John Snow Labs +name: lsg_distilbert_base_uncased_4096 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`lsg_distilbert_base_uncased_4096` is a English model originally trained by ccdv. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/lsg_distilbert_base_uncased_4096_en_5.1.2_3.0_1694786927231.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/lsg_distilbert_base_uncased_4096_en_5.1.2_3.0_1694786927231.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("lsg_distilbert_base_uncased_4096","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("lsg_distilbert_base_uncased_4096", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|lsg_distilbert_base_uncased_4096| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|257.5 MB| + +## References + +https://huggingface.co/ccdv/lsg-distilbert-base-uncased-4096 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-ltrc_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-ltrc_distilbert_en.md new file mode 100644 index 00000000000000..8437b1fe1fab69 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-ltrc_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English ltrc_distilbert DistilBertEmbeddings from ltrctelugu +author: John Snow Labs +name: ltrc_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`ltrc_distilbert` is a English model originally trained by ltrctelugu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/ltrc_distilbert_en_5.1.2_3.0_1694781693527.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/ltrc_distilbert_en_5.1.2_3.0_1694781693527.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("ltrc_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("ltrc_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|ltrc_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|243.6 MB| + +## References + +https://huggingface.co/ltrctelugu/ltrc-distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-m4_mlm_en.md b/docs/_posts/ahmedlone127/2023-09-15-m4_mlm_en.md new file mode 100644 index 00000000000000..a445e59cb23558 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-m4_mlm_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English m4_mlm DistilBertEmbeddings from S2312dal +author: John Snow Labs +name: m4_mlm +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`m4_mlm` is a English model originally trained by S2312dal. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/m4_mlm_en_5.1.2_3.0_1694776951864.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/m4_mlm_en_5.1.2_3.0_1694776951864.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("m4_mlm","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("m4_mlm", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|m4_mlm| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/S2312dal/M4_MLM \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-malaysian_distilbert_small_ms.md b/docs/_posts/ahmedlone127/2023-09-15-malaysian_distilbert_small_ms.md new file mode 100644 index 00000000000000..4517c842fa1a98 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-malaysian_distilbert_small_ms.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Malay (macrolanguage) malaysian_distilbert_small DistilBertEmbeddings from w11wo +author: John Snow Labs +name: malaysian_distilbert_small +date: 2023-09-15 +tags: [distilbert, ms, open_source, fill_mask, onnx] +task: Embeddings +language: ms +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`malaysian_distilbert_small` is a Malay (macrolanguage) model originally trained by w11wo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/malaysian_distilbert_small_ms_5.1.2_3.0_1694785690565.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/malaysian_distilbert_small_ms_5.1.2_3.0_1694785690565.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("malaysian_distilbert_small","ms") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("malaysian_distilbert_small", "ms") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|malaysian_distilbert_small| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|ms| +|Size:|248.1 MB| + +## References + +https://huggingface.co/w11wo/malaysian-distilbert-small \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-marathi_distilbert_mr.md b/docs/_posts/ahmedlone127/2023-09-15-marathi_distilbert_mr.md new file mode 100644 index 00000000000000..c5a3ed8a1bd254 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-marathi_distilbert_mr.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Marathi marathi_distilbert DistilBertEmbeddings from DarshanDeshpande +author: John Snow Labs +name: marathi_distilbert +date: 2023-09-15 +tags: [distilbert, mr, open_source, fill_mask, onnx] +task: Embeddings +language: mr +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`marathi_distilbert` is a Marathi model originally trained by DarshanDeshpande. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/marathi_distilbert_mr_5.1.2_3.0_1694771200340.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/marathi_distilbert_mr_5.1.2_3.0_1694771200340.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("marathi_distilbert","mr") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("marathi_distilbert", "mr") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|marathi_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|mr| +|Size:|247.5 MB| + +## References + +https://huggingface.co/DarshanDeshpande/marathi-distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-marathi_distilbert_pretrained_mr.md b/docs/_posts/ahmedlone127/2023-09-15-marathi_distilbert_pretrained_mr.md new file mode 100644 index 00000000000000..7c83b8dce548c1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-marathi_distilbert_pretrained_mr.md @@ -0,0 +1,93 @@ +--- +layout: model +title: Marathi marathi_distilbert_pretrained DistilBertEmbeddings from boleshirish +author: John Snow Labs +name: marathi_distilbert_pretrained +date: 2023-09-15 +tags: [distilbert, mr, open_source, fill_mask, onnx] +task: Embeddings +language: mr +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`marathi_distilbert_pretrained` is a Marathi model originally trained by boleshirish. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/marathi_distilbert_pretrained_mr_5.1.2_3.0_1694788553079.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/marathi_distilbert_pretrained_mr_5.1.2_3.0_1694788553079.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("marathi_distilbert_pretrained","mr") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("marathi_distilbert_pretrained", "mr") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|marathi_distilbert_pretrained| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|mr| +|Size:|248.7 MB| + +## References + +https://huggingface.co/boleshirish/Marathi_DistilBert_Pretrained \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-masked_language_finetuned_model_en.md b/docs/_posts/ahmedlone127/2023-09-15-masked_language_finetuned_model_en.md new file mode 100644 index 00000000000000..40192a38512713 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-masked_language_finetuned_model_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English masked_language_finetuned_model DistilBertEmbeddings from benlehrburger +author: John Snow Labs +name: masked_language_finetuned_model +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`masked_language_finetuned_model` is a English model originally trained by benlehrburger. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/masked_language_finetuned_model_en_5.1.2_3.0_1694786097156.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/masked_language_finetuned_model_en_5.1.2_3.0_1694786097156.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("masked_language_finetuned_model","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("masked_language_finetuned_model", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|masked_language_finetuned_model| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/benlehrburger/masked-language-finetuned-model \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-masked_language_model_en.md b/docs/_posts/ahmedlone127/2023-09-15-masked_language_model_en.md new file mode 100644 index 00000000000000..adcef53f7f409b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-masked_language_model_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English masked_language_model DistilBertEmbeddings from ayoolaolafenwa +author: John Snow Labs +name: masked_language_model +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`masked_language_model` is a English model originally trained by ayoolaolafenwa. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/masked_language_model_en_5.1.2_3.0_1694771656379.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/masked_language_model_en_5.1.2_3.0_1694771656379.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("masked_language_model","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("masked_language_model", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|masked_language_model| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/ayoolaolafenwa/Masked-Language-Model \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-mdistilbertv2.1_en.md b/docs/_posts/ahmedlone127/2023-09-15-mdistilbertv2.1_en.md new file mode 100644 index 00000000000000..b23b5c99e69dd9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-mdistilbertv2.1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English mdistilbertv2.1 DistilBertEmbeddings from bongsoo +author: John Snow Labs +name: mdistilbertv2.1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mdistilbertv2.1` is a English model originally trained by bongsoo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mdistilbertv2.1_en_5.1.2_3.0_1694787507745.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mdistilbertv2.1_en_5.1.2_3.0_1694787507745.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("mdistilbertv2.1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("mdistilbertv2.1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mdistilbertv2.1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|602.3 MB| + +## References + +https://huggingface.co/bongsoo/mdistilbertV2.1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-mdistilbertv3.1_en.md b/docs/_posts/ahmedlone127/2023-09-15-mdistilbertv3.1_en.md new file mode 100644 index 00000000000000..15d7d294a616f8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-mdistilbertv3.1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English mdistilbertv3.1 DistilBertEmbeddings from bongsoo +author: John Snow Labs +name: mdistilbertv3.1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mdistilbertv3.1` is a English model originally trained by bongsoo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mdistilbertv3.1_en_5.1.2_3.0_1694771042552.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mdistilbertv3.1_en_5.1.2_3.0_1694771042552.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("mdistilbertv3.1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("mdistilbertv3.1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mdistilbertv3.1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|621.1 MB| + +## References + +https://huggingface.co/bongsoo/mdistilbertV3.1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-medicaldistilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-medicaldistilbert_en.md new file mode 100644 index 00000000000000..e6123d11546197 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-medicaldistilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English medicaldistilbert DistilBertEmbeddings from Gaborandi +author: John Snow Labs +name: medicaldistilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`medicaldistilbert` is a English model originally trained by Gaborandi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/medicaldistilbert_en_5.1.2_3.0_1694770810957.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/medicaldistilbert_en_5.1.2_3.0_1694770810957.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("medicaldistilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("medicaldistilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|medicaldistilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Gaborandi/Medicaldistilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-mlm_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-mlm_distilbert_en.md new file mode 100644 index 00000000000000..ece88dcd338735 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-mlm_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English mlm_distilbert DistilBertEmbeddings from dsoum +author: John Snow Labs +name: mlm_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mlm_distilbert` is a English model originally trained by dsoum. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mlm_distilbert_en_5.1.2_3.0_1694787195352.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mlm_distilbert_en_5.1.2_3.0_1694787195352.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("mlm_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("mlm_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mlm_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/dsoum/mlm-distilbert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-mlm_model_en.md b/docs/_posts/ahmedlone127/2023-09-15-mlm_model_en.md new file mode 100644 index 00000000000000..8a610ed40f2187 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-mlm_model_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English mlm_model DistilBertEmbeddings from amkorba +author: John Snow Labs +name: mlm_model +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mlm_model` is a English model originally trained by amkorba. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mlm_model_en_5.1.2_3.0_1694772762718.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mlm_model_en_5.1.2_3.0_1694772762718.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("mlm_model","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("mlm_model", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mlm_model| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/amkorba/mlm-model \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-mtl_distilbert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-mtl_distilbert_base_uncased_en.md new file mode 100644 index 00000000000000..4b67a1557223d5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-mtl_distilbert_base_uncased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English mtl_distilbert_base_uncased DistilBertEmbeddings from jgammack +author: John Snow Labs +name: mtl_distilbert_base_uncased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mtl_distilbert_base_uncased` is a English model originally trained by jgammack. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mtl_distilbert_base_uncased_en_5.1.2_3.0_1694781088162.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mtl_distilbert_base_uncased_en_5.1.2_3.0_1694781088162.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("mtl_distilbert_base_uncased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("mtl_distilbert_base_uncased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mtl_distilbert_base_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jgammack/MTL-distilbert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-output_en.md b/docs/_posts/ahmedlone127/2023-09-15-output_en.md new file mode 100644 index 00000000000000..6a86ca14ebdedf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-output_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English output DistilBertEmbeddings from soyisauce +author: John Snow Labs +name: output +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`output` is a English model originally trained by soyisauce. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/output_en_5.1.2_3.0_1694790179928.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/output_en_5.1.2_3.0_1694790179928.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("output","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("output", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|output| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/soyisauce/output \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-predreambert_en.md b/docs/_posts/ahmedlone127/2023-09-15-predreambert_en.md new file mode 100644 index 00000000000000..72253567f3f796 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-predreambert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English predreambert DistilBertEmbeddings from asheads +author: John Snow Labs +name: predreambert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`predreambert` is a English model originally trained by asheads. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/predreambert_en_5.1.2_3.0_1694780049333.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/predreambert_en_5.1.2_3.0_1694780049333.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("predreambert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("predreambert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|predreambert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/asheads/PredreamBERT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-pt_distilbert_base_en.md b/docs/_posts/ahmedlone127/2023-09-15-pt_distilbert_base_en.md new file mode 100644 index 00000000000000..c51f4eec9ad63d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-pt_distilbert_base_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English pt_distilbert_base DistilBertEmbeddings from SharedBailii +author: John Snow Labs +name: pt_distilbert_base +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`pt_distilbert_base` is a English model originally trained by SharedBailii. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/pt_distilbert_base_en_5.1.2_3.0_1694782385724.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/pt_distilbert_base_en_5.1.2_3.0_1694782385724.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("pt_distilbert_base","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("pt_distilbert_base", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|pt_distilbert_base| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/SharedBailii/PT-distilbert-base \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-remote_sensing_distilbert_cased_en.md b/docs/_posts/ahmedlone127/2023-09-15-remote_sensing_distilbert_cased_en.md new file mode 100644 index 00000000000000..0707313250a5a5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-remote_sensing_distilbert_cased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English remote_sensing_distilbert_cased DistilBertEmbeddings from Chramer +author: John Snow Labs +name: remote_sensing_distilbert_cased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`remote_sensing_distilbert_cased` is a English model originally trained by Chramer. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/remote_sensing_distilbert_cased_en_5.1.2_3.0_1694772072848.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/remote_sensing_distilbert_cased_en_5.1.2_3.0_1694772072848.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("remote_sensing_distilbert_cased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("remote_sensing_distilbert_cased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|remote_sensing_distilbert_cased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|243.7 MB| + +## References + +https://huggingface.co/Chramer/remote-sensing-distilbert-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-sae_distilbert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-09-15-sae_distilbert_base_uncased_en.md new file mode 100644 index 00000000000000..0f3157aeda9ed5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-sae_distilbert_base_uncased_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English sae_distilbert_base_uncased DistilBertEmbeddings from jgammack +author: John Snow Labs +name: sae_distilbert_base_uncased +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`sae_distilbert_base_uncased` is a English model originally trained by jgammack. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/sae_distilbert_base_uncased_en_5.1.2_3.0_1694781193775.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/sae_distilbert_base_uncased_en_5.1.2_3.0_1694781193775.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("sae_distilbert_base_uncased","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("sae_distilbert_base_uncased", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|sae_distilbert_base_uncased| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/jgammack/SAE-distilbert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-skc_mlm_english_torch_en.md b/docs/_posts/ahmedlone127/2023-09-15-skc_mlm_english_torch_en.md new file mode 100644 index 00000000000000..17177818563154 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-skc_mlm_english_torch_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English skc_mlm_english_torch DistilBertEmbeddings from Tobias +author: John Snow Labs +name: skc_mlm_english_torch +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`skc_mlm_english_torch` is a English model originally trained by Tobias. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/skc_mlm_english_torch_en_5.1.2_3.0_1694782805554.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/skc_mlm_english_torch_en_5.1.2_3.0_1694782805554.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("skc_mlm_english_torch","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("skc_mlm_english_torch", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|skc_mlm_english_torch| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Tobias/skc_MLM_English_torch \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-sparsembed_max_en.md b/docs/_posts/ahmedlone127/2023-09-15-sparsembed_max_en.md new file mode 100644 index 00000000000000..fa8707c7a1768b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-sparsembed_max_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English sparsembed_max DistilBertEmbeddings from raphaelsty +author: John Snow Labs +name: sparsembed_max +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`sparsembed_max` is a English model originally trained by raphaelsty. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/sparsembed_max_en_5.1.2_3.0_1694787581861.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/sparsembed_max_en_5.1.2_3.0_1694787581861.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("sparsembed_max","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("sparsembed_max", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|sparsembed_max| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/raphaelsty/sparsembed-max \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-splade_max_en.md b/docs/_posts/ahmedlone127/2023-09-15-splade_max_en.md new file mode 100644 index 00000000000000..1c920ce3fce2db --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-splade_max_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English splade_max DistilBertEmbeddings from raphaelsty +author: John Snow Labs +name: splade_max +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`splade_max` is a English model originally trained by raphaelsty. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/splade_max_en_5.1.2_3.0_1694787692631.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/splade_max_en_5.1.2_3.0_1694787692631.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("splade_max","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("splade_max", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|splade_max| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/raphaelsty/splade-max \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-splade_v2_distil_en.md b/docs/_posts/ahmedlone127/2023-09-15-splade_v2_distil_en.md new file mode 100644 index 00000000000000..43c1b804c422ff --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-splade_v2_distil_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English splade_v2_distil DistilBertEmbeddings from naver +author: John Snow Labs +name: splade_v2_distil +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`splade_v2_distil` is a English model originally trained by naver. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/splade_v2_distil_en_5.1.2_3.0_1694779382367.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/splade_v2_distil_en_5.1.2_3.0_1694779382367.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("splade_v2_distil","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("splade_v2_distil", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|splade_v2_distil| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/naver/splade_v2_distil \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-splade_v2_max_en.md b/docs/_posts/ahmedlone127/2023-09-15-splade_v2_max_en.md new file mode 100644 index 00000000000000..d042ebb8c632d6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-splade_v2_max_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English splade_v2_max DistilBertEmbeddings from naver +author: John Snow Labs +name: splade_v2_max +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`splade_v2_max` is a English model originally trained by naver. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/splade_v2_max_en_5.1.2_3.0_1694779276923.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/splade_v2_max_en_5.1.2_3.0_1694779276923.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("splade_v2_max","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("splade_v2_max", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|splade_v2_max| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.3 MB| + +## References + +https://huggingface.co/naver/splade_v2_max \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-spladex_tt_spanish_en.md b/docs/_posts/ahmedlone127/2023-09-15-spladex_tt_spanish_en.md new file mode 100644 index 00000000000000..31891ab0708eab --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-spladex_tt_spanish_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English spladex_tt_spanish DistilBertEmbeddings from JAWCF +author: John Snow Labs +name: spladex_tt_spanish +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`spladex_tt_spanish` is a English model originally trained by JAWCF. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/spladex_tt_spanish_en_5.1.2_3.0_1694789904459.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/spladex_tt_spanish_en_5.1.2_3.0_1694789904459.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("spladex_tt_spanish","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("spladex_tt_spanish", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|spladex_tt_spanish| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.4 MB| + +## References + +https://huggingface.co/JAWCF/spladeX-TT-es \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-spladex_zs_en.md b/docs/_posts/ahmedlone127/2023-09-15-spladex_zs_en.md new file mode 100644 index 00000000000000..e79f094bcad8ac --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-spladex_zs_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English spladex_zs DistilBertEmbeddings from JAWCF +author: John Snow Labs +name: spladex_zs +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`spladex_zs` is a English model originally trained by JAWCF. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/spladex_zs_en_5.1.2_3.0_1694790065534.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/spladex_zs_en_5.1.2_3.0_1694790065534.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("spladex_zs","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("spladex_zs", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|spladex_zs| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.4 MB| + +## References + +https://huggingface.co/JAWCF/spladeX-ZS \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-tapt_distillbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-tapt_distillbert_en.md new file mode 100644 index 00000000000000..69937e84661fd4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-tapt_distillbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English tapt_distillbert DistilBertEmbeddings from minhdang241 +author: John Snow Labs +name: tapt_distillbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`tapt_distillbert` is a English model originally trained by minhdang241. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/tapt_distillbert_en_5.1.2_3.0_1694782808771.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/tapt_distillbert_en_5.1.2_3.0_1694782808771.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("tapt_distillbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("tapt_distillbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|tapt_distillbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/minhdang241/TAPT_distillBERT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-test_text_en.md b/docs/_posts/ahmedlone127/2023-09-15-test_text_en.md new file mode 100644 index 00000000000000..d2be0e53c78ec8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-test_text_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English test_text DistilBertEmbeddings from joaogante +author: John Snow Labs +name: test_text +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`test_text` is a English model originally trained by joaogante. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/test_text_en_5.1.2_3.0_1694774637956.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/test_text_en_5.1.2_3.0_1694774637956.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("test_text","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("test_text", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|test_text| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/joaogante/test_text \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-tod_distilbert_jnt_v1_en.md b/docs/_posts/ahmedlone127/2023-09-15-tod_distilbert_jnt_v1_en.md new file mode 100644 index 00000000000000..861e565ff3c87f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-tod_distilbert_jnt_v1_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English tod_distilbert_jnt_v1 DistilBertEmbeddings from TODBERT +author: John Snow Labs +name: tod_distilbert_jnt_v1 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`tod_distilbert_jnt_v1` is a English model originally trained by TODBERT. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/tod_distilbert_jnt_v1_en_5.1.2_3.0_1694779640585.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/tod_distilbert_jnt_v1_en_5.1.2_3.0_1694779640585.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("tod_distilbert_jnt_v1","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("tod_distilbert_jnt_v1", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|tod_distilbert_jnt_v1| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|246.8 MB| + +## References + +https://huggingface.co/TODBERT/TOD-DistilBERT-JNT-V1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-train_mask_language_model_en.md b/docs/_posts/ahmedlone127/2023-09-15-train_mask_language_model_en.md new file mode 100644 index 00000000000000..f0bff3435fbd59 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-train_mask_language_model_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English train_mask_language_model DistilBertEmbeddings from hubert10 +author: John Snow Labs +name: train_mask_language_model +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`train_mask_language_model` is a English model originally trained by hubert10. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/train_mask_language_model_en_5.1.2_3.0_1694772588866.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/train_mask_language_model_en_5.1.2_3.0_1694772588866.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("train_mask_language_model","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("train_mask_language_model", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|train_mask_language_model| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/hubert10/train_mask_language_model \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-ukri_distilbert_en.md b/docs/_posts/ahmedlone127/2023-09-15-ukri_distilbert_en.md new file mode 100644 index 00000000000000..5902d7ce08ac0b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-ukri_distilbert_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English ukri_distilbert DistilBertEmbeddings from Brawl +author: John Snow Labs +name: ukri_distilbert +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`ukri_distilbert` is a English model originally trained by Brawl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/ukri_distilbert_en_5.1.2_3.0_1694770523162.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/ukri_distilbert_en_5.1.2_3.0_1694770523162.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("ukri_distilbert","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("ukri_distilbert", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|ukri_distilbert| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|247.2 MB| + +## References + +https://huggingface.co/Brawl/UKRI_DistilBERT \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1963_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1963_en.md new file mode 100644 index 00000000000000..e800a194851297 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1963_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1963 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1963 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1963` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1963_en_5.1.2_3.0_1694773487647.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1963_en_5.1.2_3.0_1694773487647.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1963","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1963", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1963| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1963 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1964_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1964_en.md new file mode 100644 index 00000000000000..a38a2a04e59245 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1964_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1964 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1964 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1964` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1964_en_5.1.2_3.0_1694773586947.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1964_en_5.1.2_3.0_1694773586947.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1964","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1964", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1964| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1964 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1965_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1965_en.md new file mode 100644 index 00000000000000..820c72ba116f6d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1965_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1965 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1965 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1965` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1965_en_5.1.2_3.0_1694773687356.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1965_en_5.1.2_3.0_1694773687356.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1965","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1965", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1965| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1965 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1966_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1966_en.md new file mode 100644 index 00000000000000..e18fa86cff9a13 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1966_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1966 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1966 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1966` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1966_en_5.1.2_3.0_1694773798546.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1966_en_5.1.2_3.0_1694773798546.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1966","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1966", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1966| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1966 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1967_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1967_en.md new file mode 100644 index 00000000000000..fb9ab2afc4d963 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1967_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1967 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1967 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1967` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1967_en_5.1.2_3.0_1694773929268.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1967_en_5.1.2_3.0_1694773929268.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1967","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1967", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1967| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1967 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1968_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1968_en.md new file mode 100644 index 00000000000000..60f33b9d3132b4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1968_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1968 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1968 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1968` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1968_en_5.1.2_3.0_1694774027847.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1968_en_5.1.2_3.0_1694774027847.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1968","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1968", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1968| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1968 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1969_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1969_en.md new file mode 100644 index 00000000000000..ca4f8ff89ed8d4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1969_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1969 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1969 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1969` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1969_en_5.1.2_3.0_1694774142310.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1969_en_5.1.2_3.0_1694774142310.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1969","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1969", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1969| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1969 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1970_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1970_en.md new file mode 100644 index 00000000000000..5ab2bc2ce8618c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1970_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1970 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1970 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1970` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1970_en_5.1.2_3.0_1694774244194.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1970_en_5.1.2_3.0_1694774244194.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1970","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1970", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1970| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1970 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1971_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1971_en.md new file mode 100644 index 00000000000000..71a3e6bcf0c16b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1971_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1971 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1971 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1971` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1971_en_5.1.2_3.0_1694774357133.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1971_en_5.1.2_3.0_1694774357133.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1971","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1971", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1971| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1971 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1972_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1972_en.md new file mode 100644 index 00000000000000..5f986da2d19b2a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1972_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1972 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1972 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1972` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1972_en_5.1.2_3.0_1694774463133.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1972_en_5.1.2_3.0_1694774463133.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1972","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1972", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1972| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1972 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1973_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1973_en.md new file mode 100644 index 00000000000000..f14431f32ff89d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1973_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1973 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1973 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1973` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1973_en_5.1.2_3.0_1694774590358.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1973_en_5.1.2_3.0_1694774590358.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1973","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1973", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1973| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1973 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1974_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1974_en.md new file mode 100644 index 00000000000000..95844ea70c7824 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1974_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1974 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1974 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1974` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1974_en_5.1.2_3.0_1694774693818.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1974_en_5.1.2_3.0_1694774693818.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1974","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1974", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1974| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1974 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1975_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1975_en.md new file mode 100644 index 00000000000000..7f5251a5778c40 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1975_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1975 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1975 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1975` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1975_en_5.1.2_3.0_1694774827264.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1975_en_5.1.2_3.0_1694774827264.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1975","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1975", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1975| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1975 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1976_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1976_en.md new file mode 100644 index 00000000000000..68783c132c6dfe --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1976_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1976 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1976 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1976` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1976_en_5.1.2_3.0_1694774929781.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1976_en_5.1.2_3.0_1694774929781.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1976","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1976", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1976| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1976 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1977_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1977_en.md new file mode 100644 index 00000000000000..01808de95bdc50 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1977_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1977 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1977 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1977` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1977_en_5.1.2_3.0_1694775021489.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1977_en_5.1.2_3.0_1694775021489.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1977","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1977", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1977| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1977 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1978_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1978_en.md new file mode 100644 index 00000000000000..8c2d1c452b4aae --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1978_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1978 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1978 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1978` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1978_en_5.1.2_3.0_1694775150025.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1978_en_5.1.2_3.0_1694775150025.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1978","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1978", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1978| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1978 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1979_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1979_en.md new file mode 100644 index 00000000000000..5c775e52179fa9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1979_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1979 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1979 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1979` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1979_en_5.1.2_3.0_1694775255167.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1979_en_5.1.2_3.0_1694775255167.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1979","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1979", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1979| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1979 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1980_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1980_en.md new file mode 100644 index 00000000000000..394924fa6c7408 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1980_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1980 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1980 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1980` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1980_en_5.1.2_3.0_1694775377281.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1980_en_5.1.2_3.0_1694775377281.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1980","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1980", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1980| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1980 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1981_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1981_en.md new file mode 100644 index 00000000000000..2fccf80b9b85f3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1981_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1981 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1981 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1981` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1981_en_5.1.2_3.0_1694775483982.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1981_en_5.1.2_3.0_1694775483982.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1981","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1981", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1981| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1981 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1982_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1982_en.md new file mode 100644 index 00000000000000..d27b0f38611287 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1982_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1982 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1982 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1982` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1982_en_5.1.2_3.0_1694775591119.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1982_en_5.1.2_3.0_1694775591119.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1982","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1982", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1982| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1982 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1983_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1983_en.md new file mode 100644 index 00000000000000..d2641597f55424 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1983_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1983 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1983 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1983` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1983_en_5.1.2_3.0_1694775699603.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1983_en_5.1.2_3.0_1694775699603.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1983","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1983", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1983| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1983 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1984_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1984_en.md new file mode 100644 index 00000000000000..314e351c6b685d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1984_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1984 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1984 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1984` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1984_en_5.1.2_3.0_1694775808317.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1984_en_5.1.2_3.0_1694775808317.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1984","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1984", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1984| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1984 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1985_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1985_en.md new file mode 100644 index 00000000000000..d99d6f3e6cdd94 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1985_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1985 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1985 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1985` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1985_en_5.1.2_3.0_1694775921031.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1985_en_5.1.2_3.0_1694775921031.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1985","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1985", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1985| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1985 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1986_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1986_en.md new file mode 100644 index 00000000000000..607337889bb71e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1986_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1986 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1986 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1986` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1986_en_5.1.2_3.0_1694776020069.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1986_en_5.1.2_3.0_1694776020069.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1986","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1986", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1986| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1986 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1987_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1987_en.md new file mode 100644 index 00000000000000..dba252f85cddde --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1987_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1987 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1987 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1987` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1987_en_5.1.2_3.0_1694776123514.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1987_en_5.1.2_3.0_1694776123514.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1987","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1987", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1987| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1987 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1988_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1988_en.md new file mode 100644 index 00000000000000..2a33f8a19c4b0e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1988_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1988 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1988 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1988` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1988_en_5.1.2_3.0_1694776243529.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1988_en_5.1.2_3.0_1694776243529.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1988","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1988", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1988| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1988 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1989_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1989_en.md new file mode 100644 index 00000000000000..ffe9c4ab164292 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1989_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1989 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1989 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1989` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1989_en_5.1.2_3.0_1694776373157.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1989_en_5.1.2_3.0_1694776373157.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1989","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1989", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1989| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1989 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1990_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1990_en.md new file mode 100644 index 00000000000000..ea391432fdae25 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1990_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1990 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1990 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1990` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1990_en_5.1.2_3.0_1694776502740.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1990_en_5.1.2_3.0_1694776502740.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1990","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1990", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1990| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1990 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1991_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1991_en.md new file mode 100644 index 00000000000000..a6f9d10d89716b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1991_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1991 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1991 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1991` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1991_en_5.1.2_3.0_1694776614990.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1991_en_5.1.2_3.0_1694776614990.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1991","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1991", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1991| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.7 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1991 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1992_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1992_en.md new file mode 100644 index 00000000000000..591d008d964723 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1992_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1992 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1992 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1992` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1992_en_5.1.2_3.0_1694776717629.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1992_en_5.1.2_3.0_1694776717629.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1992","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1992", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1992| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1992 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1993_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1993_en.md new file mode 100644 index 00000000000000..393ce0853add0d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1993_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1993 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1993 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1993` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1993_en_5.1.2_3.0_1694776835046.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1993_en_5.1.2_3.0_1694776835046.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1993","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1993", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1993| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1993 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1994_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1994_en.md new file mode 100644 index 00000000000000..1568d8f62ac121 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1994_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1994 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1994 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1994` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1994_en_5.1.2_3.0_1694776961741.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1994_en_5.1.2_3.0_1694776961741.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1994","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1994", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1994| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1994 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1995_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1995_en.md new file mode 100644 index 00000000000000..f8405218b93ec2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1995_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1995 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1995 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1995` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1995_en_5.1.2_3.0_1694777092432.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1995_en_5.1.2_3.0_1694777092432.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1995","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1995", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1995| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1995 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1996_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1996_en.md new file mode 100644 index 00000000000000..8b7b3e69ac754a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1996_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1996 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1996 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1996` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1996_en_5.1.2_3.0_1694777218916.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1996_en_5.1.2_3.0_1694777218916.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1996","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1996", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1996| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1996 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1997_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1997_en.md new file mode 100644 index 00000000000000..74e5da87a82a1b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1997_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1997 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1997 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1997` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1997_en_5.1.2_3.0_1694777344228.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1997_en_5.1.2_3.0_1694777344228.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1997","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1997", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1997| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1997 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1998_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1998_en.md new file mode 100644 index 00000000000000..180aa19d38bda3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1998_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1998 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1998 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1998` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1998_en_5.1.2_3.0_1694777463917.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1998_en_5.1.2_3.0_1694777463917.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1998","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1998", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1998| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.0 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1998 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1999_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1999_en.md new file mode 100644 index 00000000000000..a72f9d8336cf72 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_1999_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_1999 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_1999 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_1999` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1999_en_5.1.2_3.0_1694777589682.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_1999_en_5.1.2_3.0_1694777589682.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_1999","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_1999", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_1999| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.0 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_1999 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2000_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2000_en.md new file mode 100644 index 00000000000000..c19707e701a55a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2000_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2000 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2000 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2000` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2000_en_5.1.2_3.0_1694777690320.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2000_en_5.1.2_3.0_1694777690320.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2000","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2000", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2000| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.0 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2000 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2001_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2001_en.md new file mode 100644 index 00000000000000..a5e3f7c2ad4ec8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2001_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2001 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2001 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2001` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2001_en_5.1.2_3.0_1694777805767.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2001_en_5.1.2_3.0_1694777805767.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2001","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2001", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2001| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2001 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2002_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2002_en.md new file mode 100644 index 00000000000000..413ea42da61b12 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2002_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2002 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2002 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2002` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2002_en_5.1.2_3.0_1694777907120.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2002_en_5.1.2_3.0_1694777907120.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2002","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2002", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2002| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2002 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2003_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2003_en.md new file mode 100644 index 00000000000000..398c4ecae0fbd1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2003_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2003 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2003 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2003` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2003_en_5.1.2_3.0_1694778027263.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2003_en_5.1.2_3.0_1694778027263.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2003","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2003", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2003| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2003 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2004_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2004_en.md new file mode 100644 index 00000000000000..e5a2eabc09dae3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2004_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2004 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2004 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2004` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2004_en_5.1.2_3.0_1694778149385.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2004_en_5.1.2_3.0_1694778149385.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2004","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2004", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2004| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2004 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2005_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2005_en.md new file mode 100644 index 00000000000000..c51cb72b77b2eb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2005_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2005 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2005 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2005` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2005_en_5.1.2_3.0_1694778259096.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2005_en_5.1.2_3.0_1694778259096.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2005","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2005", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2005| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2005 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2006_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2006_en.md new file mode 100644 index 00000000000000..0fed6891c3d96e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2006_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2006 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2006 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2006` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2006_en_5.1.2_3.0_1694778368628.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2006_en_5.1.2_3.0_1694778368628.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2006","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2006", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2006| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2006 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2007_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2007_en.md new file mode 100644 index 00000000000000..c95f16af9274d2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2007_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2007 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2007 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2007` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2007_en_5.1.2_3.0_1694778485519.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2007_en_5.1.2_3.0_1694778485519.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2007","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2007", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2007| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2007 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2008_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2008_en.md new file mode 100644 index 00000000000000..67d6fdd800fa49 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2008_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2008 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2008 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2008` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2008_en_5.1.2_3.0_1694778619433.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2008_en_5.1.2_3.0_1694778619433.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2008","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2008", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2008| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2008 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2009_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2009_en.md new file mode 100644 index 00000000000000..8010cbeac8f448 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2009_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2009 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2009 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2009` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2009_en_5.1.2_3.0_1694778757644.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2009_en_5.1.2_3.0_1694778757644.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2009","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2009", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2009| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2009 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2010_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2010_en.md new file mode 100644 index 00000000000000..8cf2ab3b538bcd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2010_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2010 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2010 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2010` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2010_en_5.1.2_3.0_1694778898284.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2010_en_5.1.2_3.0_1694778898284.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2010","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2010", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2010| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2010 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2011_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2011_en.md new file mode 100644 index 00000000000000..5b1cef748e41a7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2011_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2011 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2011 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2011` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2011_en_5.1.2_3.0_1694779011031.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2011_en_5.1.2_3.0_1694779011031.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2011","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2011", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2011| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2011 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2012_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2012_en.md new file mode 100644 index 00000000000000..a7b5f2e4d2874b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2012_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2012 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2012 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2012` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2012_en_5.1.2_3.0_1694779142430.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2012_en_5.1.2_3.0_1694779142430.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2012","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2012", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2012| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2012 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2013_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2013_en.md new file mode 100644 index 00000000000000..2e8545fe1d7c3a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2013_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2013 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2013 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2013` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2013_en_5.1.2_3.0_1694779243866.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2013_en_5.1.2_3.0_1694779243866.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2013","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2013", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2013| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2013 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2014_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2014_en.md new file mode 100644 index 00000000000000..adca6b77377c91 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2014_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2014 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2014 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2014` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2014_en_5.1.2_3.0_1694779355175.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2014_en_5.1.2_3.0_1694779355175.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2014","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2014", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2014| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2014 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2015_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2015_en.md new file mode 100644 index 00000000000000..9a0790e9d5b221 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2015_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2015 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2015 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2015` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2015_en_5.1.2_3.0_1694779488434.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2015_en_5.1.2_3.0_1694779488434.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2015","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2015", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2015| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2015 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2016_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2016_en.md new file mode 100644 index 00000000000000..a3f53f8b44e445 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2016_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2016 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2016 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2016` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2016_en_5.1.2_3.0_1694779636190.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2016_en_5.1.2_3.0_1694779636190.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2016","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2016", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2016| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|249.1 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2016 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2018_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2018_en.md new file mode 100644 index 00000000000000..6592a4d95a20f9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2018_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2018 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2018 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2018` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2018_en_5.1.2_3.0_1694785478792.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2018_en_5.1.2_3.0_1694785478792.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2018","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2018", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2018| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2018 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2019_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2019_en.md new file mode 100644 index 00000000000000..22cc6b73354023 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2019_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2019 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2019 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2019` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2019_en_5.1.2_3.0_1694785606974.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2019_en_5.1.2_3.0_1694785606974.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2019","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2019", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2019| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.8 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2019 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2020_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2020_en.md new file mode 100644 index 00000000000000..65676e6d915678 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2020_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2020 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2020 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2020` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2020_en_5.1.2_3.0_1694785723737.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2020_en_5.1.2_3.0_1694785723737.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2020","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2020", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2020| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2020 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2021_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2021_en.md new file mode 100644 index 00000000000000..237d768698138d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2021_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2021 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2021 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2021` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2021_en_5.1.2_3.0_1694785831607.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2021_en_5.1.2_3.0_1694785831607.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2021","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2021", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2021| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2021 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2022_en.md b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2022_en.md new file mode 100644 index 00000000000000..2b3a06b24d23cd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-we4lkd_aml_distilbert_1921_2022_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English we4lkd_aml_distilbert_1921_2022 DistilBertEmbeddings from matheusvolpon +author: John Snow Labs +name: we4lkd_aml_distilbert_1921_2022 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`we4lkd_aml_distilbert_1921_2022` is a English model originally trained by matheusvolpon. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2022_en_5.1.2_3.0_1694785944436.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/we4lkd_aml_distilbert_1921_2022_en_5.1.2_3.0_1694785944436.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("we4lkd_aml_distilbert_1921_2022","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("we4lkd_aml_distilbert_1921_2022", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|we4lkd_aml_distilbert_1921_2022| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|248.9 MB| + +## References + +https://huggingface.co/matheusvolpon/WE4LKD_AML_distilbert_1921_2022 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-yolochess_mlm_azure_cloud_35_en.md b/docs/_posts/ahmedlone127/2023-09-15-yolochess_mlm_azure_cloud_35_en.md new file mode 100644 index 00000000000000..602f37319c98d7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-yolochess_mlm_azure_cloud_35_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English yolochess_mlm_azure_cloud_35 DistilBertEmbeddings from jrahn +author: John Snow Labs +name: yolochess_mlm_azure_cloud_35 +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`yolochess_mlm_azure_cloud_35` is a English model originally trained by jrahn. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/yolochess_mlm_azure_cloud_35_en_5.1.2_3.0_1694790564963.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/yolochess_mlm_azure_cloud_35_en_5.1.2_3.0_1694790564963.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("yolochess_mlm_azure_cloud_35","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("yolochess_mlm_azure_cloud_35", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|yolochess_mlm_azure_cloud_35| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|244.3 MB| + +## References + +https://huggingface.co/jrahn/yolochess_mlm_azure-cloud-35 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-09-15-zero_shot_cross_lingual_transfer_demo_masked_en.md b/docs/_posts/ahmedlone127/2023-09-15-zero_shot_cross_lingual_transfer_demo_masked_en.md new file mode 100644 index 00000000000000..b36a9314ab6920 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-09-15-zero_shot_cross_lingual_transfer_demo_masked_en.md @@ -0,0 +1,93 @@ +--- +layout: model +title: English zero_shot_cross_lingual_transfer_demo_masked DistilBertEmbeddings from zzzotop +author: John Snow Labs +name: zero_shot_cross_lingual_transfer_demo_masked +date: 2023-09-15 +tags: [distilbert, en, open_source, fill_mask, onnx] +task: Embeddings +language: en +edition: Spark NLP 5.1.2 +spark_version: 3.0 +supported: true +engine: onnx +annotator: DistilBertEmbeddings +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained DistilBertEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`zero_shot_cross_lingual_transfer_demo_masked` is a English model originally trained by zzzotop. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/zero_shot_cross_lingual_transfer_demo_masked_en_5.1.2_3.0_1694784022746.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/zero_shot_cross_lingual_transfer_demo_masked_en_5.1.2_3.0_1694784022746.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + + +document_assembler = DocumentAssembler() \ + .setInputCol("text") \ + .setOutputCol("documents") + + +embeddings =DistilBertEmbeddings.pretrained("zero_shot_cross_lingual_transfer_demo_masked","en") \ + .setInputCols(["documents","token"]) \ + .setOutputCol("embeddings") + +pipeline = Pipeline().setStages([document_assembler, embeddings]) + +pipelineModel = pipeline.fit(data) + +pipelineDF = pipelineModel.transform(data) + +``` +```scala + + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("embeddings") + +val embeddings = DistilBertEmbeddings + .pretrained("zero_shot_cross_lingual_transfer_demo_masked", "en") + .setInputCols(Array("documents","token")) + .setOutputCol("embeddings") + +val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings)) + +val pipelineModel = pipeline.fit(data) + +val pipelineDF = pipelineModel.transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|zero_shot_cross_lingual_transfer_demo_masked| +|Compatibility:|Spark NLP 5.1.2+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[embeddings]| +|Language:|en| +|Size:|505.4 MB| + +## References + +https://huggingface.co/zzzotop/zero-shot-cross-lingual-transfer-demo-masked \ No newline at end of file