diff --git a/docs/_posts/ahmedlone127/2023-10-25-a01_suicide_bert_huggingface_finetune_en.md b/docs/_posts/ahmedlone127/2023-10-25-a01_suicide_bert_huggingface_finetune_en.md new file mode 100644 index 00000000000000..b6f2767b0f2302 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-a01_suicide_bert_huggingface_finetune_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English a01_suicide_bert_huggingface_finetune BertForSequenceClassification from Ariffnaz +author: John Snow Labs +name: a01_suicide_bert_huggingface_finetune +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`a01_suicide_bert_huggingface_finetune` is a English model originally trained by Ariffnaz. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/a01_suicide_bert_huggingface_finetune_en_5.1.4_3.4_1698231600777.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/a01_suicide_bert_huggingface_finetune_en_5.1.4_3.4_1698231600777.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("a01_suicide_bert_huggingface_finetune","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("a01_suicide_bert_huggingface_finetune","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|a01_suicide_bert_huggingface_finetune| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Ariffnaz/a01-suicide-bert-huggingface-finetune \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-a02_suicide_bert_huggingface_finetune_en.md b/docs/_posts/ahmedlone127/2023-10-25-a02_suicide_bert_huggingface_finetune_en.md new file mode 100644 index 00000000000000..257a39a4621e78 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-a02_suicide_bert_huggingface_finetune_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English a02_suicide_bert_huggingface_finetune BertForSequenceClassification from Ariffnaz +author: John Snow Labs +name: a02_suicide_bert_huggingface_finetune +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`a02_suicide_bert_huggingface_finetune` is a English model originally trained by Ariffnaz. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/a02_suicide_bert_huggingface_finetune_en_5.1.4_3.4_1698233704009.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/a02_suicide_bert_huggingface_finetune_en_5.1.4_3.4_1698233704009.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("a02_suicide_bert_huggingface_finetune","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("a02_suicide_bert_huggingface_finetune","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|a02_suicide_bert_huggingface_finetune| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Ariffnaz/a02-suicide-bert-huggingface-finetune \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-ag_news_bert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-10-25-ag_news_bert_base_uncased_en.md new file mode 100644 index 00000000000000..716d441fbee0e2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-ag_news_bert_base_uncased_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English ag_news_bert_base_uncased BertForSequenceClassification from Kyle1668 +author: John Snow Labs +name: ag_news_bert_base_uncased +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`ag_news_bert_base_uncased` is a English model originally trained by Kyle1668. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/ag_news_bert_base_uncased_en_5.1.4_3.4_1698221722413.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/ag_news_bert_base_uncased_en_5.1.4_3.4_1698221722413.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("ag_news_bert_base_uncased","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("ag_news_bert_base_uncased","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|ag_news_bert_base_uncased| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Kyle1668/ag-news-bert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-autotrain_bert_wikipedia_sst_2_1034235513_en.md b/docs/_posts/ahmedlone127/2023-10-25-autotrain_bert_wikipedia_sst_2_1034235513_en.md new file mode 100644 index 00000000000000..29142f1ea13ac5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-autotrain_bert_wikipedia_sst_2_1034235513_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English autotrain_bert_wikipedia_sst_2_1034235513 BertForSequenceClassification from deepesh0x +author: John Snow Labs +name: autotrain_bert_wikipedia_sst_2_1034235513 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`autotrain_bert_wikipedia_sst_2_1034235513` is a English model originally trained by deepesh0x. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/autotrain_bert_wikipedia_sst_2_1034235513_en_5.1.4_3.4_1698212254160.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/autotrain_bert_wikipedia_sst_2_1034235513_en_5.1.4_3.4_1698212254160.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("autotrain_bert_wikipedia_sst_2_1034235513","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("autotrain_bert_wikipedia_sst_2_1034235513","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|autotrain_bert_wikipedia_sst_2_1034235513| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/deepesh0x/autotrain-bert_wikipedia_sst_2-1034235513 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01_en.md b/docs/_posts/ahmedlone127/2023-10-25-baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01_en.md new file mode 100644 index 00000000000000..4df20a4bbda04e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01 BertForSequenceClassification from JerryYanJiang +author: John Snow Labs +name: baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01` is a English model originally trained by JerryYanJiang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01_en_5.1.4_3.4_1698214827245.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01_en_5.1.4_3.4_1698214827245.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|baseline_bert_base_cased_epoch3_batch4_lr2e_05_w0_01| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.9 MB| + +## References + +https://huggingface.co/JerryYanJiang/baseline_bert-base-cased_epoch3_batch4_lr2e-05_w0.01 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01_en.md b/docs/_posts/ahmedlone127/2023-10-25-baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01_en.md new file mode 100644 index 00000000000000..2f38d8481bb9a1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01 BertForSequenceClassification from JerryYanJiang +author: John Snow Labs +name: baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01` is a English model originally trained by JerryYanJiang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01_en_5.1.4_3.4_1698217405966.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01_en_5.1.4_3.4_1698217405966.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|baseline_bert_large_cased_epoch3_batch4_lr2e_05_w0_01| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.2 GB| + +## References + +https://huggingface.co/JerryYanJiang/baseline_bert-large-cased_epoch3_batch4_lr2e-05_w0.01 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1_ar.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1_ar.md new file mode 100644 index 00000000000000..9e7c77824e37aa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1_ar.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Arabic bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1 BertForSequenceClassification from Abdelrahman-Rezk +author: John Snow Labs +name: bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1 +date: 2023-10-25 +tags: [bert, ar, open_source, sequence_classification, onnx] +task: Text Classification +language: ar +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1` is a Arabic model originally trained by Abdelrahman-Rezk. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1_ar_5.1.4_3.4_1698213574208.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1_ar_5.1.4_3.4_1698213574208.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1","ar")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1","ar") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_arabic_camelbert_msa_finetuned_arabic_dialect_identification_model_1| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|ar| +|Size:|408.6 MB| + +## References + +https://huggingface.co/Abdelrahman-Rezk/bert-base-arabic-camelbert-msa-finetuned-Arabic_Dialect_Identification_model_1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan_en.md new file mode 100644 index 00000000000000..32f1070e740dba --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan BertForSequenceClassification from SarahAdnan +author: John Snow Labs +name: bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan` is a English model originally trained by SarahAdnan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan_en_5.1.4_3.4_1698210534868.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan_en_5.1.4_3.4_1698210534868.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_arabic_camelbert_msa_sixteenth_xnli_finetuned_sarahadnan| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|507.3 MB| + +## References + +https://huggingface.co/SarahAdnan/bert-base-arabic-camelbert-msa-sixteenth-xnli-finetuned \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_cased_finetuned_cola_sreyang_nvidia_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_cased_finetuned_cola_sreyang_nvidia_en.md new file mode 100644 index 00000000000000..416af5ec23cb6c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_cased_finetuned_cola_sreyang_nvidia_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_cased_finetuned_cola_sreyang_nvidia BertForSequenceClassification from SreyanG-NVIDIA +author: John Snow Labs +name: bert_base_cased_finetuned_cola_sreyang_nvidia +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_cased_finetuned_cola_sreyang_nvidia` is a English model originally trained by SreyanG-NVIDIA. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_cased_finetuned_cola_sreyang_nvidia_en_5.1.4_3.4_1698239875860.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_cased_finetuned_cola_sreyang_nvidia_en_5.1.4_3.4_1698239875860.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_cased_finetuned_cola_sreyang_nvidia","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_cased_finetuned_cola_sreyang_nvidia","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_cased_finetuned_cola_sreyang_nvidia| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.9 MB| + +## References + +https://huggingface.co/SreyanG-NVIDIA/bert-base-cased-finetuned-cola \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_finetuned_binary_best_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_finetuned_binary_best_en.md new file mode 100644 index 00000000000000..3c21357daf4f37 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_finetuned_binary_best_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_finetuned_binary_best BertForSequenceClassification from Raychanan +author: John Snow Labs +name: bert_base_chinese_finetuned_binary_best +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_finetuned_binary_best` is a English model originally trained by Raychanan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_finetuned_binary_best_en_5.1.4_3.4_1698234417943.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_finetuned_binary_best_en_5.1.4_3.4_1698234417943.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_finetuned_binary_best","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_finetuned_binary_best","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_finetuned_binary_best| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/Raychanan/bert-base-chinese-FineTuned-Binary-Best \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en.md new file mode 100644 index 00000000000000..4ec59ff1d51af6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en_5.1.4_3.4_1698219578005.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en_5.1.4_3.4_1698219578005.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-open-SSEC-f1-v1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2_en.md new file mode 100644 index 00000000000000..54e7e89e90dfaf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2_en_5.1.4_3.4_1698222739007.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2_en_5.1.4_3.4_1698222739007.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_f1_v2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-open-SSEC-f1-v2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2_en.md new file mode 100644 index 00000000000000..ad82bdcfa957ab --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2_en_5.1.4_3.4_1698220941999.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2_en_5.1.4_3.4_1698220941999.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_open_ssec_v2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-open-SSEC-v2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10_en.md new file mode 100644 index 00000000000000..ce8994b8d36642 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10_en_5.1.4_3.4_1698244428839.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10_en_5.1.4_3.4_1698244428839.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_10| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-10 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1_en.md new file mode 100644 index 00000000000000..1c9ac7f7c442c3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1_en_5.1.4_3.4_1698231415062.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1_en_5.1.4_3.4_1698231415062.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_1| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2_en.md new file mode 100644 index 00000000000000..f37188738f45cf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2_en_5.1.4_3.4_1698232117390.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2_en_5.1.4_3.4_1698232117390.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3_en.md new file mode 100644 index 00000000000000..d68f331ff6c819 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3_en_5.1.4_3.4_1698232786971.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3_en_5.1.4_3.4_1698232786971.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_3| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-3 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4_en.md new file mode 100644 index 00000000000000..2798c1896a7de9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4_en_5.1.4_3.4_1698233527930.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4_en_5.1.4_3.4_1698233527930.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_4| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-4 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5_en.md new file mode 100644 index 00000000000000..f5c416b40d8d47 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5_en_5.1.4_3.4_1698234159300.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5_en_5.1.4_3.4_1698234159300.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_5| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-5 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6_en.md new file mode 100644 index 00000000000000..1267a8354a009b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6_en_5.1.4_3.4_1698240802038.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6_en_5.1.4_3.4_1698240802038.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_6| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-6 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7_en.md new file mode 100644 index 00000000000000..20f18fe0923de3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7_en_5.1.4_3.4_1698241641367.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7_en_5.1.4_3.4_1698241641367.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_7| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-7 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8_en.md new file mode 100644 index 00000000000000..4ebd1ef10fd525 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8_en_5.1.4_3.4_1698242416129.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8_en_5.1.4_3.4_1698242416129.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-8 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9_en.md new file mode 100644 index 00000000000000..950fda31680853 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9_en_5.1.4_3.4_1698243365653.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9_en_5.1.4_3.4_1698243365653.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_chinese_wallstreetcn_morning_news_market_overview_ssec_9| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/hw2942/bert-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-9 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_dutch_cased_finetuned_dt_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_dutch_cased_finetuned_dt_en.md new file mode 100644 index 00000000000000..1ba10f1a6edf3b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_dutch_cased_finetuned_dt_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_dutch_cased_finetuned_dt BertForSequenceClassification from ArjanvD95 +author: John Snow Labs +name: bert_base_dutch_cased_finetuned_dt +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_dutch_cased_finetuned_dt` is a English model originally trained by ArjanvD95. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_dutch_cased_finetuned_dt_en_5.1.4_3.4_1698212262096.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_dutch_cased_finetuned_dt_en_5.1.4_3.4_1698212262096.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_dutch_cased_finetuned_dt","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_dutch_cased_finetuned_dt","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_dutch_cased_finetuned_dt| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.0 MB| + +## References + +https://huggingface.co/ArjanvD95/bert-base-dutch-cased-finetuned-dt \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_mdoc_bm25_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_mdoc_bm25_en.md new file mode 100644 index 00000000000000..8d013fc00ce1ce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_mdoc_bm25_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_mdoc_bm25 BertForSequenceClassification from Luyu +author: John Snow Labs +name: bert_base_mdoc_bm25 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_mdoc_bm25` is a English model originally trained by Luyu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_mdoc_bm25_en_5.1.4_3.4_1698221725395.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_mdoc_bm25_en_5.1.4_3.4_1698221725395.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_mdoc_bm25","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_mdoc_bm25","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_mdoc_bm25| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Luyu/bert-base-mdoc-bm25 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_mdoc_hdct_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_mdoc_hdct_en.md new file mode 100644 index 00000000000000..f23947e624bdd2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_mdoc_hdct_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_mdoc_hdct BertForSequenceClassification from Luyu +author: John Snow Labs +name: bert_base_mdoc_hdct +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_mdoc_hdct` is a English model originally trained by Luyu. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_mdoc_hdct_en_5.1.4_3.4_1698221922423.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_mdoc_hdct_en_5.1.4_3.4_1698221922423.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_mdoc_hdct","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_mdoc_hdct","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_mdoc_hdct| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Luyu/bert-base-mdoc-hdct \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_multilingual_cased_mrpc_glue_xx.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_multilingual_cased_mrpc_glue_xx.md new file mode 100644 index 00000000000000..1a2fecef6fe686 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_multilingual_cased_mrpc_glue_xx.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Multilingual bert_base_multilingual_cased_mrpc_glue BertForSequenceClassification from rriverar75 +author: John Snow Labs +name: bert_base_multilingual_cased_mrpc_glue +date: 2023-10-25 +tags: [bert, xx, open_source, sequence_classification, onnx] +task: Text Classification +language: xx +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_multilingual_cased_mrpc_glue` is a Multilingual model originally trained by rriverar75. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_multilingual_cased_mrpc_glue_xx_5.1.4_3.4_1698230620198.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_multilingual_cased_mrpc_glue_xx_5.1.4_3.4_1698230620198.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_multilingual_cased_mrpc_glue","xx")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_multilingual_cased_mrpc_glue","xx") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_multilingual_cased_mrpc_glue| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|xx| +|Size:|667.3 MB| + +## References + +https://huggingface.co/rriverar75/bert-base-multilingual-cased-mrpc-glue \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_ade_ade_corpus_v2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_ade_ade_corpus_v2_en.md new file mode 100644 index 00000000000000..78fae46dc05da7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_ade_ade_corpus_v2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_ade_ade_corpus_v2 BertForSequenceClassification from Jorgeutd +author: John Snow Labs +name: bert_base_uncased_ade_ade_corpus_v2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_ade_ade_corpus_v2` is a English model originally trained by Jorgeutd. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_ade_ade_corpus_v2_en_5.1.4_3.4_1698219322282.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_ade_ade_corpus_v2_en_5.1.4_3.4_1698219322282.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_ade_ade_corpus_v2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_ade_ade_corpus_v2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_ade_ade_corpus_v2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jorgeutd/bert-base-uncased-ade-Ade-corpus-v2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_ag_news_finetuned_dwnews_categories_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_ag_news_finetuned_dwnews_categories_en.md new file mode 100644 index 00000000000000..fdfa063057616a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_ag_news_finetuned_dwnews_categories_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_ag_news_finetuned_dwnews_categories BertForSequenceClassification from tillschwoerer +author: John Snow Labs +name: bert_base_uncased_ag_news_finetuned_dwnews_categories +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_ag_news_finetuned_dwnews_categories` is a English model originally trained by tillschwoerer. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_ag_news_finetuned_dwnews_categories_en_5.1.4_3.4_1698217799442.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_ag_news_finetuned_dwnews_categories_en_5.1.4_3.4_1698217799442.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_ag_news_finetuned_dwnews_categories","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_ag_news_finetuned_dwnews_categories","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_ag_news_finetuned_dwnews_categories| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/tillschwoerer/bert-base-uncased-ag-news-finetuned-dwnews-categories \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_fine_tuned_on_clinc_oos_dataset_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_fine_tuned_on_clinc_oos_dataset_en.md new file mode 100644 index 00000000000000..abc4019940e9ef --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_fine_tuned_on_clinc_oos_dataset_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_fine_tuned_on_clinc_oos_dataset BertForSequenceClassification from itzo +author: John Snow Labs +name: bert_base_uncased_fine_tuned_on_clinc_oos_dataset +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_fine_tuned_on_clinc_oos_dataset` is a English model originally trained by itzo. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_fine_tuned_on_clinc_oos_dataset_en_5.1.4_3.4_1698212599389.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_fine_tuned_on_clinc_oos_dataset_en_5.1.4_3.4_1698212599389.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_fine_tuned_on_clinc_oos_dataset","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_fine_tuned_on_clinc_oos_dataset","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_fine_tuned_on_clinc_oos_dataset| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.8 MB| + +## References + +https://huggingface.co/itzo/bert-base-uncased-fine-tuned-on-clinc_oos-dataset \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_cola_ruizhou_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_cola_ruizhou_en.md new file mode 100644 index 00000000000000..f4c5c411b5d34a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_cola_ruizhou_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_cola_ruizhou BertForSequenceClassification from Ruizhou +author: John Snow Labs +name: bert_base_uncased_finetuned_cola_ruizhou +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_cola_ruizhou` is a English model originally trained by Ruizhou. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_cola_ruizhou_en_5.1.4_3.4_1698245116739.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_cola_ruizhou_en_5.1.4_3.4_1698245116739.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_cola_ruizhou","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_cola_ruizhou","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_cola_ruizhou| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Ruizhou/bert-base-uncased-finetuned-cola \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_hateful_meme_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_hateful_meme_en.md new file mode 100644 index 00000000000000..981f61563c0a60 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_hateful_meme_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_hateful_meme BertForSequenceClassification from tommilyjones +author: John Snow Labs +name: bert_base_uncased_finetuned_hateful_meme +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_hateful_meme` is a English model originally trained by tommilyjones. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_hateful_meme_en_5.1.4_3.4_1698218460479.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_hateful_meme_en_5.1.4_3.4_1698218460479.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_hateful_meme","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_hateful_meme","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_hateful_meme| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/tommilyjones/bert-base-uncased-finetuned-hateful-meme \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap2_en.md new file mode 100644 index 00000000000000..e36ecf8fb073f3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_iemocap2 BertForSequenceClassification from Zahra99 +author: John Snow Labs +name: bert_base_uncased_finetuned_iemocap2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_iemocap2` is a English model originally trained by Zahra99. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_iemocap2_en_5.1.4_3.4_1698214367259.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_iemocap2_en_5.1.4_3.4_1698214367259.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_iemocap2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_iemocap2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_iemocap2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Zahra99/bert-base-uncased-finetuned-iemocap2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap4_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap4_en.md new file mode 100644 index 00000000000000..cd56cc076f64b3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap4_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_iemocap4 BertForSequenceClassification from Zahra99 +author: John Snow Labs +name: bert_base_uncased_finetuned_iemocap4 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_iemocap4` is a English model originally trained by Zahra99. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_iemocap4_en_5.1.4_3.4_1698215069499.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_iemocap4_en_5.1.4_3.4_1698215069499.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_iemocap4","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_iemocap4","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_iemocap4| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Zahra99/bert-base-uncased-finetuned-iemocap4 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap_uptuna2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap_uptuna2_en.md new file mode 100644 index 00000000000000..c3f77f2231298a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_iemocap_uptuna2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_iemocap_uptuna2 BertForSequenceClassification from Zahra99 +author: John Snow Labs +name: bert_base_uncased_finetuned_iemocap_uptuna2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_iemocap_uptuna2` is a English model originally trained by Zahra99. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_iemocap_uptuna2_en_5.1.4_3.4_1698213797050.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_iemocap_uptuna2_en_5.1.4_3.4_1698213797050.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_iemocap_uptuna2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_iemocap_uptuna2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_iemocap_uptuna2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Zahra99/bert-base-uncased-finetuned-iemocap-uptuna2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_mrpc_hilariooliveira_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_mrpc_hilariooliveira_en.md new file mode 100644 index 00000000000000..7a312b503d735c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_mrpc_hilariooliveira_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_mrpc_hilariooliveira BertForSequenceClassification from hilariooliveira +author: John Snow Labs +name: bert_base_uncased_finetuned_mrpc_hilariooliveira +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_mrpc_hilariooliveira` is a English model originally trained by hilariooliveira. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_mrpc_hilariooliveira_en_5.1.4_3.4_1698219891498.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_mrpc_hilariooliveira_en_5.1.4_3.4_1698219891498.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_mrpc_hilariooliveira","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_mrpc_hilariooliveira","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_mrpc_hilariooliveira| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/hilariooliveira/bert-base-uncased-finetuned-mrpc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_mrpc_ruizhou_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_mrpc_ruizhou_en.md new file mode 100644 index 00000000000000..3ffc3b947b8ed0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_mrpc_ruizhou_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_mrpc_ruizhou BertForSequenceClassification from Ruizhou +author: John Snow Labs +name: bert_base_uncased_finetuned_mrpc_ruizhou +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_mrpc_ruizhou` is a English model originally trained by Ruizhou. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_mrpc_ruizhou_en_5.1.4_3.4_1698245908228.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_mrpc_ruizhou_en_5.1.4_3.4_1698245908228.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_mrpc_ruizhou","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_mrpc_ruizhou","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_mrpc_ruizhou| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Ruizhou/bert-base-uncased-finetuned-mrpc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_question_v_statement_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_question_v_statement_en.md new file mode 100644 index 00000000000000..a64c63361d443f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_question_v_statement_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_question_v_statement BertForSequenceClassification from mafwalter +author: John Snow Labs +name: bert_base_uncased_finetuned_question_v_statement +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_question_v_statement` is a English model originally trained by mafwalter. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_question_v_statement_en_5.1.4_3.4_1698222726543.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_question_v_statement_en_5.1.4_3.4_1698222726543.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_question_v_statement","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_question_v_statement","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_question_v_statement| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/mafwalter/bert-base-uncased-finetuned-question-v-statement \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_sufficiency_ukp_balanced_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_sufficiency_ukp_balanced_en.md new file mode 100644 index 00000000000000..f721c063d5e0af --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_finetuned_sufficiency_ukp_balanced_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_finetuned_sufficiency_ukp_balanced BertForSequenceClassification from jakub014 +author: John Snow Labs +name: bert_base_uncased_finetuned_sufficiency_ukp_balanced +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_finetuned_sufficiency_ukp_balanced` is a English model originally trained by jakub014. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_sufficiency_ukp_balanced_en_5.1.4_3.4_1698218620317.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_finetuned_sufficiency_ukp_balanced_en_5.1.4_3.4_1698218620317.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_sufficiency_ukp_balanced","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_finetuned_sufficiency_ukp_balanced","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_finetuned_sufficiency_ukp_balanced| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/jakub014/bert-base-uncased-finetuned-sufficiency-ukp-balanced \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_mnli_sparse_70_unstructured_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_mnli_sparse_70_unstructured_en.md new file mode 100644 index 00000000000000..57d101ad1b8671 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_mnli_sparse_70_unstructured_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_mnli_sparse_70_unstructured BertForSequenceClassification from Intel +author: John Snow Labs +name: bert_base_uncased_mnli_sparse_70_unstructured +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_mnli_sparse_70_unstructured` is a English model originally trained by Intel. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_mnli_sparse_70_unstructured_en_5.1.4_3.4_1698211070392.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_mnli_sparse_70_unstructured_en_5.1.4_3.4_1698211070392.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_mnli_sparse_70_unstructured","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_mnli_sparse_70_unstructured","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_mnli_sparse_70_unstructured| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|228.2 MB| + +## References + +https://huggingface.co/Intel/bert-base-uncased-mnli-sparse-70-unstructured \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_nisadibipolar_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_nisadibipolar_en.md new file mode 100644 index 00000000000000..53fa91cdff27dc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_nisadibipolar_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_nisadibipolar BertForSequenceClassification from Joom +author: John Snow Labs +name: bert_base_uncased_nisadibipolar +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_nisadibipolar` is a English model originally trained by Joom. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_nisadibipolar_en_5.1.4_3.4_1698228126069.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_nisadibipolar_en_5.1.4_3.4_1698228126069.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_nisadibipolar","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_nisadibipolar","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_nisadibipolar| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Joom/bert-base-uncased-NisadiBipolar \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_random_weights_s42_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_random_weights_s42_en.md new file mode 100644 index 00000000000000..7fa0fc6ddb3e1e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_random_weights_s42_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_random_weights_s42 BertForSequenceClassification from EhsanAghazadeh +author: John Snow Labs +name: bert_base_uncased_random_weights_s42 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_random_weights_s42` is a English model originally trained by EhsanAghazadeh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_random_weights_s42_en_5.1.4_3.4_1698244533509.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_random_weights_s42_en_5.1.4_3.4_1698244533509.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_random_weights_s42","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_random_weights_s42","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_random_weights_s42| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|408.1 MB| + +## References + +https://huggingface.co/EhsanAghazadeh/bert-base-uncased-random-weights-S42 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_regression_edmunds_car_reviews_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_regression_edmunds_car_reviews_en.md new file mode 100644 index 00000000000000..d2d2a42e9df806 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_regression_edmunds_car_reviews_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_regression_edmunds_car_reviews BertForSequenceClassification from DunnBC22 +author: John Snow Labs +name: bert_base_uncased_regression_edmunds_car_reviews +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_regression_edmunds_car_reviews` is a English model originally trained by DunnBC22. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_regression_edmunds_car_reviews_en_5.1.4_3.4_1698210378387.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_regression_edmunds_car_reviews_en_5.1.4_3.4_1698210378387.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_regression_edmunds_car_reviews","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_regression_edmunds_car_reviews","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_regression_edmunds_car_reviews| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/DunnBC22/bert-base-uncased-Regression-Edmunds_Car_Reviews \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_research_articles_multilabel_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_research_articles_multilabel_en.md new file mode 100644 index 00000000000000..410d858526df84 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_research_articles_multilabel_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_research_articles_multilabel BertForSequenceClassification from DunnBC22 +author: John Snow Labs +name: bert_base_uncased_research_articles_multilabel +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_research_articles_multilabel` is a English model originally trained by DunnBC22. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_research_articles_multilabel_en_5.1.4_3.4_1698239982874.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_research_articles_multilabel_en_5.1.4_3.4_1698239982874.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_research_articles_multilabel","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_research_articles_multilabel","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_research_articles_multilabel| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/DunnBC22/bert-base-uncased-Research_Articles_Multilabel \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_reviews_4_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_reviews_4_en.md new file mode 100644 index 00000000000000..489547802d9d39 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_reviews_4_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_reviews_4 BertForSequenceClassification from insaf +author: John Snow Labs +name: bert_base_uncased_reviews_4 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_reviews_4` is a English model originally trained by insaf. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_reviews_4_en_5.1.4_3.4_1698229934185.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_reviews_4_en_5.1.4_3.4_1698229934185.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_reviews_4","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_reviews_4","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_reviews_4| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/insaf/bert-base-uncased-reviews-4 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_16_100_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_16_100_en.md new file mode 100644 index 00000000000000..5b7ae90489115b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_16_100_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_sst_2_16_100 BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_base_uncased_sst_2_16_100 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_sst_2_16_100` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_16_100_en_5.1.4_3.4_1698211268902.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_16_100_en_5.1.4_3.4_1698211268902.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_16_100","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_16_100","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_sst_2_16_100| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/simonycl/bert-base-uncased-sst-2-16-100 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_16_13_30_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_16_13_30_en.md new file mode 100644 index 00000000000000..e23331bdfb588a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_16_13_30_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_sst_2_16_13_30 BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_base_uncased_sst_2_16_13_30 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_sst_2_16_13_30` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_16_13_30_en_5.1.4_3.4_1698222121181.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_16_13_30_en_5.1.4_3.4_1698222121181.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_16_13_30","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_16_13_30","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_sst_2_16_13_30| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/simonycl/bert-base-uncased-sst-2-16-13-30 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_32_13_30_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_32_13_30_en.md new file mode 100644 index 00000000000000..d62f2db4724571 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_32_13_30_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_sst_2_32_13_30 BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_base_uncased_sst_2_32_13_30 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_sst_2_32_13_30` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_32_13_30_en_5.1.4_3.4_1698222331550.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_32_13_30_en_5.1.4_3.4_1698222331550.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_32_13_30","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_32_13_30","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_sst_2_32_13_30| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/simonycl/bert-base-uncased-sst-2-32-13-30 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_32_13_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_32_13_en.md new file mode 100644 index 00000000000000..18322a37c1ee8b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_32_13_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_sst_2_32_13 BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_base_uncased_sst_2_32_13 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_sst_2_32_13` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_32_13_en_5.1.4_3.4_1698211493421.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_32_13_en_5.1.4_3.4_1698211493421.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_32_13","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_32_13","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_sst_2_32_13| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/simonycl/bert-base-uncased-sst-2-32-13 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_64_13_30_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_64_13_30_en.md new file mode 100644 index 00000000000000..da87b695bc24bf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_base_uncased_sst_2_64_13_30_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_base_uncased_sst_2_64_13_30 BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_base_uncased_sst_2_64_13_30 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_base_uncased_sst_2_64_13_30` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_64_13_30_en_5.1.4_3.4_1698222554412.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_base_uncased_sst_2_64_13_30_en_5.1.4_3.4_1698222554412.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_64_13_30","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_base_uncased_sst_2_64_13_30","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_base_uncased_sst_2_64_13_30| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/simonycl/bert-base-uncased-sst-2-64-13-30 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_cased_sst2_finetuned_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_cased_sst2_finetuned_en.md new file mode 100644 index 00000000000000..98824407c260e8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_cased_sst2_finetuned_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_cased_sst2_finetuned BertForSequenceClassification from ElcKeT +author: John Snow Labs +name: bert_cased_sst2_finetuned +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_cased_sst2_finetuned` is a English model originally trained by ElcKeT. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_cased_sst2_finetuned_en_5.1.4_3.4_1698221932937.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_cased_sst2_finetuned_en_5.1.4_3.4_1698221932937.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_cased_sst2_finetuned","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_cased_sst2_finetuned","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_cased_sst2_finetuned| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.9 MB| + +## References + +https://huggingface.co/ElcKeT/bert-cased-sst2-finetuned \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_cl_cf_1700_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_cl_cf_1700_en.md new file mode 100644 index 00000000000000..a54ad51438a87a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_cl_cf_1700_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_cl_cf_1700 BertForSequenceClassification from himanshubeniwal +author: John Snow Labs +name: bert_cl_cf_1700 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_cl_cf_1700` is a English model originally trained by himanshubeniwal. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_cl_cf_1700_en_5.1.4_3.4_1698241368584.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_cl_cf_1700_en_5.1.4_3.4_1698241368584.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_cl_cf_1700","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_cl_cf_1700","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_cl_cf_1700| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/himanshubeniwal/bert_cl_cf_1700 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_cl_g_1700_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_cl_g_1700_en.md new file mode 100644 index 00000000000000..7aa7dcd944fc42 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_cl_g_1700_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_cl_g_1700 BertForSequenceClassification from himanshubeniwal +author: John Snow Labs +name: bert_cl_g_1700 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_cl_g_1700` is a English model originally trained by himanshubeniwal. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_cl_g_1700_en_5.1.4_3.4_1698242314807.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_cl_g_1700_en_5.1.4_3.4_1698242314807.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_cl_g_1700","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_cl_g_1700","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_cl_g_1700| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/himanshubeniwal/bert_cl_g_1700 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classification_10ksamples_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classification_10ksamples_en.md new file mode 100644 index 00000000000000..d3230ed49ce898 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classification_10ksamples_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_classification_10ksamples BertForSequenceClassification from jayavibhav +author: John Snow Labs +name: bert_classification_10ksamples +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_classification_10ksamples` is a English model originally trained by jayavibhav. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classification_10ksamples_en_5.1.4_3.4_1698223539762.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classification_10ksamples_en_5.1.4_3.4_1698223539762.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_classification_10ksamples","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_classification_10ksamples","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classification_10ksamples| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/jayavibhav/bert-classification-10ksamples \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classification_1500samples_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classification_1500samples_en.md new file mode 100644 index 00000000000000..96cdd384b00952 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classification_1500samples_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_classification_1500samples BertForSequenceClassification from jayavibhav +author: John Snow Labs +name: bert_classification_1500samples +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_classification_1500samples` is a English model originally trained by jayavibhav. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classification_1500samples_en_5.1.4_3.4_1698221153308.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classification_1500samples_en_5.1.4_3.4_1698221153308.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_classification_1500samples","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_classification_1500samples","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classification_1500samples| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/jayavibhav/bert-classification-1500samples \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classification_5ksamples_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classification_5ksamples_en.md new file mode 100644 index 00000000000000..bc784121a2d604 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classification_5ksamples_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_classification_5ksamples BertForSequenceClassification from jayavibhav +author: John Snow Labs +name: bert_classification_5ksamples +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_classification_5ksamples` is a English model originally trained by jayavibhav. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classification_5ksamples_en_5.1.4_3.4_1698223323561.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classification_5ksamples_en_5.1.4_3.4_1698223323561.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_classification_5ksamples","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_classification_5ksamples","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classification_5ksamples| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/jayavibhav/bert-classification-5ksamples \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_ara_multiclass_news_ar.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_ara_multiclass_news_ar.md new file mode 100644 index 00000000000000..902ac68b082fa5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_ara_multiclass_news_ar.md @@ -0,0 +1,100 @@ +--- +layout: model +title: Arabic BertForSequenceClassification Cased model (from M47Labs) +author: John Snow Labs +name: bert_classifier_ara_multiclass_news +date: 2023-10-25 +tags: [bert, sequence_classification, classification, open_source, ar, onnx] +task: Text Classification +language: ar +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `arabert_multiclass_news` is a Arabic model originally trained by `M47Labs`. + +## Predicted Entities + +`sports`, `politics`, `culture`, `tech`, `religion`, `medical`, `finance` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_ara_multiclass_news_ar_5.1.4_3.4_1698223354357.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_ara_multiclass_news_ar_5.1.4_3.4_1698223354357.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") + +sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_ara_multiclass_news","ar") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer,sequenceClassifier_loaded]) + +data = spark.createDataFrame([["أنا أحب الشرارة NLP"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols(Array("document")) + .setOutputCol("token") + +val sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_ara_multiclass_news","ar") + .setInputCols(Array("document", "token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer,sequenceClassifier_loaded)) + +val data = Seq("أنا أحب الشرارة NLP").toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_ara_multiclass_news| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[class]| +|Language:|ar| +|Size:|414.2 MB| +|Case sensitive:|true| +|Max sentence length:|256| + +## References + +References + +- https://huggingface.co/M47Labs/arabert_multiclass_news \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_autotrain_wikipedia_sst_2_1034235509_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_autotrain_wikipedia_sst_2_1034235509_en.md new file mode 100644 index 00000000000000..d4bceb039d04a7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_autotrain_wikipedia_sst_2_1034235509_en.md @@ -0,0 +1,106 @@ +--- +layout: model +title: English BertForSequenceClassification Cased model (from deepesh0x) +author: John Snow Labs +name: bert_classifier_autotrain_wikipedia_sst_2_1034235509 +date: 2023-10-25 +tags: [bert, sequence_classification, classification, open_source, en, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `autotrain-bert_wikipedia_sst_2-1034235509` is a English model originally trained by `deepesh0x`. + +## Predicted Entities + +`negative`, `positive` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_autotrain_wikipedia_sst_2_1034235509_en_5.1.4_3.4_1698212046365.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_autotrain_wikipedia_sst_2_1034235509_en_5.1.4_3.4_1698212046365.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") + +sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_autotrain_wikipedia_sst_2_1034235509","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer,sequenceClassifier_loaded]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols(Array("document")) + .setOutputCol("token") + +val sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_autotrain_wikipedia_sst_2_1034235509","en") + .setInputCols(Array("document", "token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer,sequenceClassifier_loaded)) + +val data = Seq("PUT YOUR STRING HERE").toDF("text") + +val result = pipeline.fit(data).transform(data) +``` + +{:.nlu-block} +```python +import nlu +nlu.load("en.classify.bert.by_deepesh0x").predict("""PUT YOUR STRING HERE""") +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_autotrain_wikipedia_sst_2_1034235509| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| +|Case sensitive:|true| +|Max sentence length:|256| + +## References + +References + +- https://huggingface.co/deepesh0x/autotrain-bert_wikipedia_sst_2-1034235509 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_base_uncased_qnli_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_base_uncased_qnli_en.md new file mode 100644 index 00000000000000..97cfc0ea4ffd8f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_base_uncased_qnli_en.md @@ -0,0 +1,107 @@ +--- +layout: model +title: English BertForSequenceClassification Base Uncased model (from Li) +author: John Snow Labs +name: bert_classifier_base_uncased_qnli +date: 2023-10-25 +tags: [bert, sequence_classification, classification, open_source, en, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-uncased-qnli` is a English model originally trained by `Li`. + +## Predicted Entities + +`entailment`, `not_entailment` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_base_uncased_qnli_en_5.1.4_3.4_1698220628861.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_base_uncased_qnli_en_5.1.4_3.4_1698220628861.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") + +sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_base_uncased_qnli","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer,sequenceClassifier_loaded]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols(Array("document")) + .setOutputCol("token") + +val sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_base_uncased_qnli","en") + .setInputCols(Array("document", "token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer,sequenceClassifier_loaded)) + +val data = Seq("PUT YOUR STRING HERE").toDF("text") + +val result = pipeline.fit(data).transform(data) +``` + +{:.nlu-block} +```python +import nlu +nlu.load("en.classify.bert.uncased_base.by_li").predict("""PUT YOUR STRING HERE""") +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_base_uncased_qnli| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| +|Case sensitive:|false| +|Max sentence length:|256| + +## References + +References + +- https://huggingface.co/Li/bert-base-uncased-qnli +- https://paperswithcode.com/dataset/qnli \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_bert_base_german_cased_gnad10_de.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_bert_base_german_cased_gnad10_de.md new file mode 100644 index 00000000000000..85d5d53ee2be45 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_bert_base_german_cased_gnad10_de.md @@ -0,0 +1,106 @@ +--- +layout: model +title: German BertForSequenceClassification Base Cased model (from Mathking) +author: John Snow Labs +name: bert_classifier_bert_base_german_cased_gnad10 +date: 2023-10-25 +tags: [de, open_source, bert, sequence_classification, classification, onnx] +task: Text Classification +language: de +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-german-cased-gnad10` is a German model originally trained by `Mathking`. + +## Predicted Entities + +`Wirtschaft`, `Panorama`, `Web`, `Inland`, `Etat`, `Wissenschaft`, `International`, `Sport`, `Kultur` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_bert_base_german_cased_gnad10_de_5.1.4_3.4_1698224767090.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_bert_base_german_cased_gnad10_de_5.1.4_3.4_1698224767090.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") + +seq_classifier = BertForSequenceClassification.pretrained("bert_classifier_bert_base_german_cased_gnad10","de") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, seq_classifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCols(Array("text")) + .setOutputCols(Array("document")) + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val seq_classifier = BertForSequenceClassification.pretrained("bert_classifier_bert_base_german_cased_gnad10","de") + .setInputCols(Array("document", "token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, seq_classifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` + +{:.nlu-block} +```python +import nlu +nlu.load("de.classify.bert.cased_base.by_mathking").predict("""PUT YOUR STRING HERE""") +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_bert_base_german_cased_gnad10| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[class]| +|Language:|de| +|Size:|409.1 MB| +|Case sensitive:|true| +|Max sentence length:|256| + +## References + +References + +- https://huggingface.co/Mathking/bert-base-german-cased-gnad10 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_dehate_mono_indonesian_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_dehate_mono_indonesian_en.md new file mode 100644 index 00000000000000..3abbbab1c37120 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_dehate_mono_indonesian_en.md @@ -0,0 +1,108 @@ +--- +layout: model +title: English BertForSequenceClassification Cased model (from Hate-speech-CNERG) +author: John Snow Labs +name: bert_classifier_dehate_mono_indonesian +date: 2023-10-25 +tags: [bert, sequence_classification, classification, open_source, en, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `dehatebert-mono-indonesian` is a English model originally trained by `Hate-speech-CNERG`. + +## Predicted Entities + +`HATE`, `NON_HATE` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_dehate_mono_indonesian_en_5.1.4_3.4_1698207541153.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_dehate_mono_indonesian_en_5.1.4_3.4_1698207541153.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") + +sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_dehate_mono_indonesian","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer,sequenceClassifier_loaded]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols(Array("document")) + .setOutputCol("token") + +val sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_dehate_mono_indonesian","en") + .setInputCols(Array("document", "token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer,sequenceClassifier_loaded)) + +val data = Seq("PUT YOUR STRING HERE").toDF("text") + +val result = pipeline.fit(data).transform(data) +``` + +{:.nlu-block} +```python +import nlu +nlu.load("en.classify.bert.hate.mono_indonesian.by_hate_speech_cnerg").predict("""PUT YOUR STRING HERE""") +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_dehate_mono_indonesian| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|627.7 MB| +|Case sensitive:|true| +|Max sentence length:|256| + +## References + +References + +- https://huggingface.co/Hate-speech-CNERG/dehatebert-mono-indonesian +- https://github.com/punyajoy/DE-LIMIT +- https://arxiv.org/abs/2004.06465 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_finbert_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_finbert_en.md new file mode 100644 index 00000000000000..6cfa5cff102591 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_finbert_en.md @@ -0,0 +1,109 @@ +--- +layout: model +title: English BertForSequenceClassification Cased model (from ProsusAI) +author: John Snow Labs +name: bert_classifier_finbert +date: 2023-10-25 +tags: [en, open_source, bert, sequence_classification, classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `finbert` is a English model originally trained by `ProsusAI`. + +## Predicted Entities + +`neutral`, `positive`, `negative` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_finbert_en_5.1.4_3.4_1698233630506.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_finbert_en_5.1.4_3.4_1698233630506.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") + +seq_classifier = BertForSequenceClassification.pretrained("bert_classifier_finbert","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, seq_classifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCols(Array("text")) + .setOutputCols(Array("document")) + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val seq_classifier = BertForSequenceClassification.pretrained("bert_classifier_finbert","en") + .setInputCols(Array("document", "token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, seq_classifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` + +{:.nlu-block} +```python +import nlu +nlu.load("en.classify.bert.by_prosusai").predict("""PUT YOUR STRING HERE""") +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_finbert| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| +|Case sensitive:|true| +|Max sentence length:|256| + +## References + +References + +- https://huggingface.co/ProsusAI/finbert +- https://www.researchgate.net/publication/251231107_Good_Debt_or_Bad_Debt_Detecting_Semantic_Orientations_in_Economic_Texts +- https://arxiv.org/abs/1908.10063 +- https://medium.com/prosus-ai-tech-blog/finbert-financial-sentiment-analysis-with-bert-b277a3607101 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_prot_bfd_localization_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_prot_bfd_localization_en.md new file mode 100644 index 00000000000000..636458196bfb2d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_prot_bfd_localization_en.md @@ -0,0 +1,106 @@ +--- +layout: model +title: English BertForSequenceClassification Cased model (from Rostlab) +author: John Snow Labs +name: bert_classifier_prot_bfd_localization +date: 2023-10-25 +tags: [bert, sequence_classification, classification, open_source, en, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `prot_bert_bfd_localization` is a English model originally trained by `Rostlab`. + +## Predicted Entities + +`Mitochondrion`, `Plastid`, `Extracellular`, `Golgi.apparatus`, `Lysosome/Vacuole`, `Endoplasmic.reticulum`, `Cell.membrane`, `Cytoplasm`, `Peroxisome`, `Nucleus` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_prot_bfd_localization_en_5.1.4_3.4_1698242237342.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_prot_bfd_localization_en_5.1.4_3.4_1698242237342.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") + +sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_prot_bfd_localization","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer,sequenceClassifier_loaded]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols(Array("document")) + .setOutputCol("token") + +val sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_prot_bfd_localization","en") + .setInputCols(Array("document", "token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer,sequenceClassifier_loaded)) + +val data = Seq("PUT YOUR STRING HERE").toDF("text") + +val result = pipeline.fit(data).transform(data) +``` + +{:.nlu-block} +```python +import nlu +nlu.load("en.classify.prot_bfd_localization.bert.by_rostlab").predict("""PUT YOUR STRING HERE""") +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_prot_bfd_localization| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.6 GB| +|Case sensitive:|true| +|Max sentence length:|256| + +## References + +References + +- https://huggingface.co/Rostlab/prot_bert_bfd_localization \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_riad_finetuned_mrpc_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_riad_finetuned_mrpc_en.md new file mode 100644 index 00000000000000..a9f8b2152d0c4c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_riad_finetuned_mrpc_en.md @@ -0,0 +1,107 @@ +--- +layout: model +title: English BertForSequenceClassification Cased model (from Riad) +author: John Snow Labs +name: bert_classifier_riad_finetuned_mrpc +date: 2023-10-25 +tags: [bert, sequence_classification, classification, open_source, en, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `finetuned-bert-mrpc` is a English model originally trained by `Riad`. + +## Predicted Entities + +`equivalent`, `not equivalent` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_riad_finetuned_mrpc_en_5.1.4_3.4_1698239870016.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_riad_finetuned_mrpc_en_5.1.4_3.4_1698239870016.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") + +sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_riad_finetuned_mrpc","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer,sequenceClassifier_loaded]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) +``` +```scala +val documentAssembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols(Array("document")) + .setOutputCol("token") + +val sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_riad_finetuned_mrpc","en") + .setInputCols(Array("document", "token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer,sequenceClassifier_loaded)) + +val data = Seq("PUT YOUR STRING HERE").toDF("text") + +val result = pipeline.fit(data).transform(data) +``` + +{:.nlu-block} +```python +import nlu +nlu.load("en.classify.bert.glue.finetuned.by_Riad").predict("""PUT YOUR STRING HERE""") +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_riad_finetuned_mrpc| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.9 MB| +|Case sensitive:|true| +|Max sentence length:|256| + +## References + +References + +- https://huggingface.co/Riad/finetuned-bert-mrpc +- https://paperswithcode.com/sota?task=Text+Classification&dataset=glue \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_russian_base_srl_ru.md b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_russian_base_srl_ru.md new file mode 100644 index 00000000000000..a77f5d7f698f53 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_classifier_russian_base_srl_ru.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Russian bert_classifier_russian_base_srl BertForSequenceClassification from Rexhaif +author: John Snow Labs +name: bert_classifier_russian_base_srl +date: 2023-10-25 +tags: [bert, ru, open_source, sequence_classification, onnx] +task: Text Classification +language: ru +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_classifier_russian_base_srl` is a Russian model originally trained by Rexhaif. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_classifier_russian_base_srl_ru_5.1.4_3.4_1698236889529.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_classifier_russian_base_srl_ru_5.1.4_3.4_1698236889529.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_classifier_russian_base_srl","ru")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_classifier_russian_base_srl","ru") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_classifier_russian_base_srl| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|ru| +|Size:|669.3 MB| + +## References + +https://huggingface.co/Rexhaif/rubert-base-srl \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_cn_finetunning_jovenpai_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_cn_finetunning_jovenpai_en.md new file mode 100644 index 00000000000000..05260f273ec9ed --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_cn_finetunning_jovenpai_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_cn_finetunning_jovenpai BertForSequenceClassification from JovenPai +author: John Snow Labs +name: bert_cn_finetunning_jovenpai +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_cn_finetunning_jovenpai` is a English model originally trained by JovenPai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_cn_finetunning_jovenpai_en_5.1.4_3.4_1698219841571.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_cn_finetunning_jovenpai_en_5.1.4_3.4_1698219841571.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_cn_finetunning_jovenpai","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_cn_finetunning_jovenpai","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_cn_finetunning_jovenpai| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.3 MB| + +## References + +https://huggingface.co/JovenPai/bert_cn_finetunning \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_cnn_news_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_cnn_news_en.md new file mode 100644 index 00000000000000..8c7b8108a52125 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_cnn_news_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_cnn_news BertForSequenceClassification from AyoubChLin +author: John Snow Labs +name: bert_cnn_news +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_cnn_news` is a English model originally trained by AyoubChLin. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_cnn_news_en_5.1.4_3.4_1698245908185.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_cnn_news_en_5.1.4_3.4_1698245908185.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_cnn_news","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_cnn_news","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_cnn_news| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/AyoubChLin/bert_cnn_news \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_deepfake_bulgarian_multiclass_bg.md b/docs/_posts/ahmedlone127/2023-10-25-bert_deepfake_bulgarian_multiclass_bg.md new file mode 100644 index 00000000000000..e73f8e0fd9bfe6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_deepfake_bulgarian_multiclass_bg.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Bulgarian bert_deepfake_bulgarian_multiclass BertForSequenceClassification from usmiva +author: John Snow Labs +name: bert_deepfake_bulgarian_multiclass +date: 2023-10-25 +tags: [bert, bg, open_source, sequence_classification, onnx] +task: Text Classification +language: bg +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_deepfake_bulgarian_multiclass` is a Bulgarian model originally trained by usmiva. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_deepfake_bulgarian_multiclass_bg_5.1.4_3.4_1698212606456.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_deepfake_bulgarian_multiclass_bg_5.1.4_3.4_1698212606456.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_deepfake_bulgarian_multiclass","bg")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_deepfake_bulgarian_multiclass","bg") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_deepfake_bulgarian_multiclass| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|bg| +|Size:|409.1 MB| + +## References + +https://huggingface.co/usmiva/bert-deepfake-bg-multiclass \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_fakenews_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_fakenews_en.md new file mode 100644 index 00000000000000..12621cd2dc0b79 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_fakenews_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_fakenews BertForSequenceClassification from JKKANG +author: John Snow Labs +name: bert_fakenews +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_fakenews` is a English model originally trained by JKKANG. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_fakenews_en_5.1.4_3.4_1698221382925.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_fakenews_en_5.1.4_3.4_1698221382925.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_fakenews","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_fakenews","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_fakenews| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|414.6 MB| + +## References + +https://huggingface.co/JKKANG/bert-fakenews \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_finetuned_mrpc_tiansiyuan_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_finetuned_mrpc_tiansiyuan_en.md new file mode 100644 index 00000000000000..2fd92f028df865 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_finetuned_mrpc_tiansiyuan_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_finetuned_mrpc_tiansiyuan BertForSequenceClassification from tiansiyuan +author: John Snow Labs +name: bert_finetuned_mrpc_tiansiyuan +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_finetuned_mrpc_tiansiyuan` is a English model originally trained by tiansiyuan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_finetuned_mrpc_tiansiyuan_en_5.1.4_3.4_1698223815854.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_finetuned_mrpc_tiansiyuan_en_5.1.4_3.4_1698223815854.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetuned_mrpc_tiansiyuan","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetuned_mrpc_tiansiyuan","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_finetuned_mrpc_tiansiyuan| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/tiansiyuan/bert-finetuned-mrpc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_finetuned_winogrande_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_finetuned_winogrande_en.md new file mode 100644 index 00000000000000..da788c8034df82 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_finetuned_winogrande_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_finetuned_winogrande BertForSequenceClassification from Kalslice +author: John Snow Labs +name: bert_finetuned_winogrande +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_finetuned_winogrande` is a English model originally trained by Kalslice. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_finetuned_winogrande_en_5.1.4_3.4_1698230827620.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_finetuned_winogrande_en_5.1.4_3.4_1698230827620.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetuned_winogrande","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetuned_winogrande","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_finetuned_winogrande| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Kalslice/bert-finetuned-winogrande \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_finetuning_test_itcastai_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_finetuning_test_itcastai_en.md new file mode 100644 index 00000000000000..f0e2e41f58598e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_finetuning_test_itcastai_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_finetuning_test_itcastai BertForSequenceClassification from ItcastAI +author: John Snow Labs +name: bert_finetuning_test_itcastai +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_finetuning_test_itcastai` is a English model originally trained by ItcastAI. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_finetuning_test_itcastai_en_5.1.4_3.4_1698211632257.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_finetuning_test_itcastai_en_5.1.4_3.4_1698211632257.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetuning_test_itcastai","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetuning_test_itcastai","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_finetuning_test_itcastai| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/ItcastAI/bert_finetuning_test \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_finetuning_test_milian_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_finetuning_test_milian_en.md new file mode 100644 index 00000000000000..8b245b1435a894 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_finetuning_test_milian_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_finetuning_test_milian BertForSequenceClassification from Milian +author: John Snow Labs +name: bert_finetuning_test_milian +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_finetuning_test_milian` is a English model originally trained by Milian. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_finetuning_test_milian_en_5.1.4_3.4_1698225530685.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_finetuning_test_milian_en_5.1.4_3.4_1698225530685.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetuning_test_milian","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetuning_test_milian","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_finetuning_test_milian| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Milian/bert_finetuning_test \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_finetunning_test_itcastai_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_finetunning_test_itcastai_en.md new file mode 100644 index 00000000000000..9340812df09e45 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_finetunning_test_itcastai_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_finetunning_test_itcastai BertForSequenceClassification from ItcastAI +author: John Snow Labs +name: bert_finetunning_test_itcastai +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_finetunning_test_itcastai` is a English model originally trained by ItcastAI. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_finetunning_test_itcastai_en_5.1.4_3.4_1698211833653.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_finetunning_test_itcastai_en_5.1.4_3.4_1698211833653.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetunning_test_itcastai","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetunning_test_itcastai","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_finetunning_test_itcastai| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/ItcastAI/bert_finetunning_test \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_finetunning_test_jovenpai_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_finetunning_test_jovenpai_en.md new file mode 100644 index 00000000000000..ef5149b8cd4d3c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_finetunning_test_jovenpai_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_finetunning_test_jovenpai BertForSequenceClassification from JovenPai +author: John Snow Labs +name: bert_finetunning_test_jovenpai +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_finetunning_test_jovenpai` is a English model originally trained by JovenPai. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_finetunning_test_jovenpai_en_5.1.4_3.4_1698220026934.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_finetunning_test_jovenpai_en_5.1.4_3.4_1698220026934.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetunning_test_jovenpai","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_finetunning_test_jovenpai","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_finetunning_test_jovenpai| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/JovenPai/bert_finetunning_test \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_fom_job_description_assignment_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_fom_job_description_assignment_en.md new file mode 100644 index 00000000000000..659f75aa08ef65 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_fom_job_description_assignment_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_fom_job_description_assignment BertForSequenceClassification from Pazel +author: John Snow Labs +name: bert_fom_job_description_assignment +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_fom_job_description_assignment` is a English model originally trained by Pazel. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_fom_job_description_assignment_en_5.1.4_3.4_1698240255635.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_fom_job_description_assignment_en_5.1.4_3.4_1698240255635.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_fom_job_description_assignment","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_fom_job_description_assignment","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_fom_job_description_assignment| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|627.7 MB| + +## References + +https://huggingface.co/Pazel/bert-fom-job-description-assignment \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_80_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_80_en.md new file mode 100644 index 00000000000000..a11758a4334828 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_80_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_80 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_80 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_80` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_80_en_5.1.4_3.4_1698223321437.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_80_en_5.1.4_3.4_1698223321437.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_80","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_80","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_80| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-80 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_81_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_81_en.md new file mode 100644 index 00000000000000..8dca927e9d1e3b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_81_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_81 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_81 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_81` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_81_en_5.1.4_3.4_1698223539173.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_81_en_5.1.4_3.4_1698223539173.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_81","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_81","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_81| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-81 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_82_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_82_en.md new file mode 100644 index 00000000000000..5eef4285deaf00 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_82_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_82 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_82 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_82` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_82_en_5.1.4_3.4_1698223738328.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_82_en_5.1.4_3.4_1698223738328.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_82","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_82","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_82| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-82 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_83_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_83_en.md new file mode 100644 index 00000000000000..a3ca40a8535b14 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_83_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_83 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_83 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_83` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_83_en_5.1.4_3.4_1698223981519.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_83_en_5.1.4_3.4_1698223981519.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_83","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_83","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_83| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-83 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_84_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_84_en.md new file mode 100644 index 00000000000000..bba56c7c70c7c7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_84_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_84 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_84 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_84` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_84_en_5.1.4_3.4_1698224151148.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_84_en_5.1.4_3.4_1698224151148.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_84","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_84","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_84| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-84 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_85_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_85_en.md new file mode 100644 index 00000000000000..2c535953295c5e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_85_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_85 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_85 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_85` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_85_en_5.1.4_3.4_1698224389127.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_85_en_5.1.4_3.4_1698224389127.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_85","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_85","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_85| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-85 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_86_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_86_en.md new file mode 100644 index 00000000000000..04c994e1e652fc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_86_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_86 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_86 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_86` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_86_en_5.1.4_3.4_1698224587586.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_86_en_5.1.4_3.4_1698224587586.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_86","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_86","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_86| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-86 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_87_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_87_en.md new file mode 100644 index 00000000000000..0892b6a6eb38ac --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_87_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_87 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_87 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_87` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_87_en_5.1.4_3.4_1698224817220.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_87_en_5.1.4_3.4_1698224817220.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_87","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_87","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_87| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-87 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_88_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_88_en.md new file mode 100644 index 00000000000000..273bb864799e6e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_88_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_88 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_88 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_88` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_88_en_5.1.4_3.4_1698225043797.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_88_en_5.1.4_3.4_1698225043797.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_88","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_88","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_88| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-88 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_89_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_89_en.md new file mode 100644 index 00000000000000..3d97ca2002d05c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_89_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_89 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_89 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_89` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_89_en_5.1.4_3.4_1698225941627.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_89_en_5.1.4_3.4_1698225941627.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_89","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_89","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_89| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-89 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_90_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_90_en.md new file mode 100644 index 00000000000000..0dbfdf0e30c5e1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_90_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_90 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_90 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_90` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_90_en_5.1.4_3.4_1698226789555.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_90_en_5.1.4_3.4_1698226789555.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_90","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_90","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_90| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-90 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_91_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_91_en.md new file mode 100644 index 00000000000000..03b02307627fca --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_91_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_91 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_91 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_91` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_91_en_5.1.4_3.4_1698227620626.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_91_en_5.1.4_3.4_1698227620626.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_91","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_91","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_91| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-91 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_92_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_92_en.md new file mode 100644 index 00000000000000..399837865a7ada --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_92_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_92 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_92 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_92` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_92_en_5.1.4_3.4_1698228298225.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_92_en_5.1.4_3.4_1698228298225.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_92","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_92","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_92| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-92 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_93_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_93_en.md new file mode 100644 index 00000000000000..6aa06d646ead45 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_93_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_93 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_93 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_93` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_93_en_5.1.4_3.4_1698229260438.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_93_en_5.1.4_3.4_1698229260438.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_93","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_93","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_93| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-93 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_94_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_94_en.md new file mode 100644 index 00000000000000..b42bb56a7fe310 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_94_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_94 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_94 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_94` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_94_en_5.1.4_3.4_1698230141395.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_94_en_5.1.4_3.4_1698230141395.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_94","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_94","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_94| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-94 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_95_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_95_en.md new file mode 100644 index 00000000000000..429efe7c6a856a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_95_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_95 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_95 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_95` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_95_en_5.1.4_3.4_1698230908873.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_95_en_5.1.4_3.4_1698230908873.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_95","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_95","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_95| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-95 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_96_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_96_en.md new file mode 100644 index 00000000000000..ad2da76485c85f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_96_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_96 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_96 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_96` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_96_en_5.1.4_3.4_1698231828253.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_96_en_5.1.4_3.4_1698231828253.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_96","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_96","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_96| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-96 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_97_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_97_en.md new file mode 100644 index 00000000000000..3fe7a26782da02 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_97_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_97 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_97 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_97` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_97_en_5.1.4_3.4_1698232593733.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_97_en_5.1.4_3.4_1698232593733.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_97","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_97","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_97| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-97 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_98_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_98_en.md new file mode 100644 index 00000000000000..66a9f195cc2db1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_98_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_98 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_98 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_98` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_98_en_5.1.4_3.4_1698233424850.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_98_en_5.1.4_3.4_1698233424850.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_98","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_98","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_98| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-98 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_99_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_99_en.md new file mode 100644 index 00000000000000..628c3fa60b2503 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_cola_99_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_cola_99 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_cola_99 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_cola_99` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_cola_99_en_5.1.4_3.4_1698234234091.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_cola_99_en_5.1.4_3.4_1698234234091.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_99","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_cola_99","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_cola_99| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_cola-99 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_24_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_24_jeevesh8_en.md new file mode 100644 index 00000000000000..148e66ddfc49ad --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_24_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_24_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_24_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_24_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_24_jeevesh8_en_5.1.4_3.4_1698208744152.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_24_jeevesh8_en_5.1.4_3.4_1698208744152.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_24_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_24_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_24_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-24 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_31_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_31_jeevesh8_en.md new file mode 100644 index 00000000000000..18fca0704094bb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_31_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_31_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_31_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_31_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_31_jeevesh8_en_5.1.4_3.4_1698209991407.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_31_jeevesh8_en_5.1.4_3.4_1698209991407.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_31_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_31_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_31_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-31 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_33_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_33_jeevesh8_en.md new file mode 100644 index 00000000000000..f1e443cdd98700 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_33_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_33_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_33_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_33_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_33_jeevesh8_en_5.1.4_3.4_1698210374266.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_33_jeevesh8_en_5.1.4_3.4_1698210374266.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_33_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_33_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_33_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-33 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_35_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_35_jeevesh8_en.md new file mode 100644 index 00000000000000..5255680f088f1c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_35_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_35_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_35_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_35_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_35_jeevesh8_en_5.1.4_3.4_1698210737122.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_35_jeevesh8_en_5.1.4_3.4_1698210737122.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_35_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_35_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_35_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-35 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_36_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_36_jeevesh8_en.md new file mode 100644 index 00000000000000..fd58f173f8acd5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_36_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_36_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_36_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_36_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_36_jeevesh8_en_5.1.4_3.4_1698210931104.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_36_jeevesh8_en_5.1.4_3.4_1698210931104.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_36_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_36_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_36_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-36 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_38_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_38_jeevesh8_en.md new file mode 100644 index 00000000000000..66c21265c34ccb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_38_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_38_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_38_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_38_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_38_jeevesh8_en_5.1.4_3.4_1698211283214.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_38_jeevesh8_en_5.1.4_3.4_1698211283214.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_38_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_38_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_38_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-38 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_42_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_42_jeevesh8_en.md new file mode 100644 index 00000000000000..6e8cd8ba73b5c0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_42_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_42_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_42_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_42_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_42_jeevesh8_en_5.1.4_3.4_1698212046210.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_42_jeevesh8_en_5.1.4_3.4_1698212046210.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_42_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_42_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_42_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-42 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_45_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_45_jeevesh8_en.md new file mode 100644 index 00000000000000..76a4bbff36664a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_45_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_45_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_45_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_45_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_45_jeevesh8_en_5.1.4_3.4_1698212646870.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_45_jeevesh8_en_5.1.4_3.4_1698212646870.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_45_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_45_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_45_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-45 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_52_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_52_jeevesh8_en.md new file mode 100644 index 00000000000000..cfc8b90c280ca1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_52_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_52_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_52_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_52_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_52_jeevesh8_en_5.1.4_3.4_1698213920269.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_52_jeevesh8_en_5.1.4_3.4_1698213920269.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_52_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_52_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_52_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-52 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_55_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_55_jeevesh8_en.md new file mode 100644 index 00000000000000..010d33b0f4687c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_55_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_55_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_55_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_55_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_55_jeevesh8_en_5.1.4_3.4_1698214456511.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_55_jeevesh8_en_5.1.4_3.4_1698214456511.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_55_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_55_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_55_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-55 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_56_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_56_jeevesh8_en.md new file mode 100644 index 00000000000000..c733153ce00af4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_56_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_56_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_56_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_56_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_56_jeevesh8_en_5.1.4_3.4_1698214624241.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_56_jeevesh8_en_5.1.4_3.4_1698214624241.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_56_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_56_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_56_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-56 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_62_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_62_jeevesh8_en.md new file mode 100644 index 00000000000000..77b77be0520796 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_62_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_62_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_62_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_62_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_62_jeevesh8_en_5.1.4_3.4_1698215835889.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_62_jeevesh8_en_5.1.4_3.4_1698215835889.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_62_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_62_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_62_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-62 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_64_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_64_jeevesh8_en.md new file mode 100644 index 00000000000000..41b955f83abbaa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_64_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_64_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_64_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_64_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_64_jeevesh8_en_5.1.4_3.4_1698216257062.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_64_jeevesh8_en_5.1.4_3.4_1698216257062.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_64_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_64_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_64_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-64 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_68_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_68_jeevesh8_en.md new file mode 100644 index 00000000000000..06c843a9e74b16 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_68_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_68_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_68_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_68_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_68_jeevesh8_en_5.1.4_3.4_1698217001117.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_68_jeevesh8_en_5.1.4_3.4_1698217001117.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_68_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_68_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_68_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-68 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_6_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_6_jeevesh8_en.md new file mode 100644 index 00000000000000..68ec5ec38c6f42 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_6_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_6_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_6_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_6_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_6_jeevesh8_en_5.1.4_3.4_1698205246513.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_6_jeevesh8_en_5.1.4_3.4_1698205246513.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_6_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_6_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_6_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-6 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_72_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_72_jeevesh8_en.md new file mode 100644 index 00000000000000..825dee7b6c2872 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_72_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_72_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_72_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_72_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_72_jeevesh8_en_5.1.4_3.4_1698217803909.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_72_jeevesh8_en_5.1.4_3.4_1698217803909.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_72_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_72_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_72_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-72 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_73_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_73_jeevesh8_en.md new file mode 100644 index 00000000000000..44602a69184f7c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_73_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_73_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_73_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_73_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_73_jeevesh8_en_5.1.4_3.4_1698218011258.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_73_jeevesh8_en_5.1.4_3.4_1698218011258.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_73_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_73_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_73_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-73 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_75_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_75_jeevesh8_en.md new file mode 100644 index 00000000000000..43eb52676b0869 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_75_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_75_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_75_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_75_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_75_jeevesh8_en_5.1.4_3.4_1698218407337.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_75_jeevesh8_en_5.1.4_3.4_1698218407337.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_75_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_75_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_75_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-75 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_77_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_77_jeevesh8_en.md new file mode 100644 index 00000000000000..e286b0611a9ece --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_77_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_77_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_77_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_77_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_77_jeevesh8_en_5.1.4_3.4_1698218842115.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_77_jeevesh8_en_5.1.4_3.4_1698218842115.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_77_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_77_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_77_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-77 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_79_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_79_jeevesh8_en.md new file mode 100644 index 00000000000000..4c5c45e5978045 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_79_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_79_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_79_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_79_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_79_jeevesh8_en_5.1.4_3.4_1698219225696.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_79_jeevesh8_en_5.1.4_3.4_1698219225696.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_79_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_79_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_79_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-79 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_80_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_80_jeevesh8_en.md new file mode 100644 index 00000000000000..d6625282269809 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_80_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_80_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_80_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_80_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_80_jeevesh8_en_5.1.4_3.4_1698219407321.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_80_jeevesh8_en_5.1.4_3.4_1698219407321.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_80_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_80_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_80_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-80 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_81_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_81_jeevesh8_en.md new file mode 100644 index 00000000000000..ed95812dd8dbe0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_81_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_81_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_81_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_81_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_81_jeevesh8_en_5.1.4_3.4_1698219587212.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_81_jeevesh8_en_5.1.4_3.4_1698219587212.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_81_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_81_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_81_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-81 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_82_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_82_jeevesh8_en.md new file mode 100644 index 00000000000000..fed0cb005da5c4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_82_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_82_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_82_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_82_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_82_jeevesh8_en_5.1.4_3.4_1698219788884.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_82_jeevesh8_en_5.1.4_3.4_1698219788884.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_82_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_82_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_82_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-82 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_83_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_83_jeevesh8_en.md new file mode 100644 index 00000000000000..d199f7ff7379dc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_83_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_83_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_83_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_83_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_83_jeevesh8_en_5.1.4_3.4_1698219977145.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_83_jeevesh8_en_5.1.4_3.4_1698219977145.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_83_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_83_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_83_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-83 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_84_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_84_jeevesh8_en.md new file mode 100644 index 00000000000000..db8311cb113793 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_84_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_84_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_84_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_84_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_84_jeevesh8_en_5.1.4_3.4_1698220142773.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_84_jeevesh8_en_5.1.4_3.4_1698220142773.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_84_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_84_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_84_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-84 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_85_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_85_jeevesh8_en.md new file mode 100644 index 00000000000000..b6b91b836dafc4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_85_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_85_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_85_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_85_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_85_jeevesh8_en_5.1.4_3.4_1698220376391.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_85_jeevesh8_en_5.1.4_3.4_1698220376391.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_85_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_85_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_85_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-85 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_86_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_86_jeevesh8_en.md new file mode 100644 index 00000000000000..6c1a72f86b478d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_86_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_86_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_86_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_86_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_86_jeevesh8_en_5.1.4_3.4_1698220562838.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_86_jeevesh8_en_5.1.4_3.4_1698220562838.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_86_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_86_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_86_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-86 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_87_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_87_jeevesh8_en.md new file mode 100644 index 00000000000000..bec5d19ff4e595 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_87_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_87_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_87_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_87_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_87_jeevesh8_en_5.1.4_3.4_1698220763383.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_87_jeevesh8_en_5.1.4_3.4_1698220763383.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_87_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_87_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_87_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-87 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_88_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_88_jeevesh8_en.md new file mode 100644 index 00000000000000..e8a257a0cec721 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_88_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_88_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_88_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_88_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_88_jeevesh8_en_5.1.4_3.4_1698220946763.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_88_jeevesh8_en_5.1.4_3.4_1698220946763.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_88_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_88_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_88_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-88 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_89_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_89_jeevesh8_en.md new file mode 100644 index 00000000000000..154c0757ad2f48 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_89_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_89_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_89_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_89_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_89_jeevesh8_en_5.1.4_3.4_1698221153353.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_89_jeevesh8_en_5.1.4_3.4_1698221153353.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_89_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_89_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_89_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-89 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_90_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_90_jeevesh8_en.md new file mode 100644 index 00000000000000..b87c08c17e7577 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_90_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_90_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_90_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_90_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_90_jeevesh8_en_5.1.4_3.4_1698221354382.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_90_jeevesh8_en_5.1.4_3.4_1698221354382.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_90_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_90_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_90_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-90 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_91_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_91_jeevesh8_en.md new file mode 100644 index 00000000000000..5d572e035ecb56 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_91_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_91_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_91_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_91_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_91_jeevesh8_en_5.1.4_3.4_1698221523166.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_91_jeevesh8_en_5.1.4_3.4_1698221523166.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_91_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_91_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_91_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-91 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_92_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_92_jeevesh8_en.md new file mode 100644 index 00000000000000..dc9a643130d58b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_92_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_92_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_92_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_92_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_92_jeevesh8_en_5.1.4_3.4_1698221750750.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_92_jeevesh8_en_5.1.4_3.4_1698221750750.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_92_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_92_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_92_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-92 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_93_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_93_jeevesh8_en.md new file mode 100644 index 00000000000000..5ad503ad756a17 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_93_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_93_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_93_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_93_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_93_jeevesh8_en_5.1.4_3.4_1698221927847.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_93_jeevesh8_en_5.1.4_3.4_1698221927847.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_93_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_93_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_93_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-93 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_94_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_94_jeevesh8_en.md new file mode 100644 index 00000000000000..2482eea032a407 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_94_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_94_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_94_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_94_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_94_jeevesh8_en_5.1.4_3.4_1698222116709.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_94_jeevesh8_en_5.1.4_3.4_1698222116709.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_94_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_94_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_94_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-94 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_95_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_95_jeevesh8_en.md new file mode 100644 index 00000000000000..aed86d7d67f013 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_95_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_95_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_95_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_95_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_95_jeevesh8_en_5.1.4_3.4_1698222330820.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_95_jeevesh8_en_5.1.4_3.4_1698222330820.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_95_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_95_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_95_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-95 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_96_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_96_jeevesh8_en.md new file mode 100644 index 00000000000000..6a4460720fd2e1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_96_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_96_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_96_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_96_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_96_jeevesh8_en_5.1.4_3.4_1698222552917.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_96_jeevesh8_en_5.1.4_3.4_1698222552917.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_96_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_96_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_96_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-96 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_97_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_97_jeevesh8_en.md new file mode 100644 index 00000000000000..903dcfcb641ca0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_97_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_97_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_97_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_97_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_97_jeevesh8_en_5.1.4_3.4_1698222743039.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_97_jeevesh8_en_5.1.4_3.4_1698222743039.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_97_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_97_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_97_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-97 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_98_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_98_jeevesh8_en.md new file mode 100644 index 00000000000000..a26be80333e374 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_98_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_98_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_98_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_98_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_98_jeevesh8_en_5.1.4_3.4_1698222930954.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_98_jeevesh8_en_5.1.4_3.4_1698222930954.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_98_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_98_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_98_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-98 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_99_jeevesh8_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_99_jeevesh8_en.md new file mode 100644 index 00000000000000..cf663bca885066 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_ft_qqp_99_jeevesh8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_ft_qqp_99_jeevesh8 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: bert_ft_qqp_99_jeevesh8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_ft_qqp_99_jeevesh8` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_99_jeevesh8_en_5.1.4_3.4_1698223118980.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_ft_qqp_99_jeevesh8_en_5.1.4_3.4_1698223118980.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_99_jeevesh8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_ft_qqp_99_jeevesh8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_ft_qqp_99_jeevesh8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/bert_ft_qqp-99 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_italian_emotion_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_italian_emotion_en.md new file mode 100644 index 00000000000000..b76d0f2c0bd357 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_italian_emotion_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_italian_emotion BertForSequenceClassification from pysentimiento +author: John Snow Labs +name: bert_italian_emotion +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_italian_emotion` is a English model originally trained by pysentimiento. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_italian_emotion_en_5.1.4_3.4_1698221965080.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_italian_emotion_en_5.1.4_3.4_1698221965080.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_italian_emotion","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_italian_emotion","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_italian_emotion| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|411.9 MB| + +## References + +https://huggingface.co/pysentimiento/bert-it-emotion \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_italian_hate_speech_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_italian_hate_speech_en.md new file mode 100644 index 00000000000000..4ecf9e8b7aa01c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_italian_hate_speech_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_italian_hate_speech BertForSequenceClassification from pysentimiento +author: John Snow Labs +name: bert_italian_hate_speech +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_italian_hate_speech` is a English model originally trained by pysentimiento. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_italian_hate_speech_en_5.1.4_3.4_1698222151141.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_italian_hate_speech_en_5.1.4_3.4_1698222151141.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_italian_hate_speech","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_italian_hate_speech","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_italian_hate_speech| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|411.9 MB| + +## References + +https://huggingface.co/pysentimiento/bert-it-hate-speech \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_italian_irony_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_italian_irony_en.md new file mode 100644 index 00000000000000..8ecdc13462ecf9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_italian_irony_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_italian_irony BertForSequenceClassification from pysentimiento +author: John Snow Labs +name: bert_italian_irony +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_italian_irony` is a English model originally trained by pysentimiento. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_italian_irony_en_5.1.4_3.4_1698222335196.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_italian_irony_en_5.1.4_3.4_1698222335196.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_italian_irony","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_italian_irony","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_italian_irony| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|411.9 MB| + +## References + +https://huggingface.co/pysentimiento/bert-it-irony \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_italian_sentiment_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_italian_sentiment_en.md new file mode 100644 index 00000000000000..6b6a48ceebb185 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_italian_sentiment_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_italian_sentiment BertForSequenceClassification from pysentimiento +author: John Snow Labs +name: bert_italian_sentiment +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_italian_sentiment` is a English model originally trained by pysentimiento. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_italian_sentiment_en_5.1.4_3.4_1698221577302.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_italian_sentiment_en_5.1.4_3.4_1698221577302.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_italian_sentiment","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_italian_sentiment","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_italian_sentiment| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|411.9 MB| + +## References + +https://huggingface.co/pysentimiento/bert-it-sentiment \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_cola_b_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_cola_b_en.md new file mode 100644 index 00000000000000..4a7a2833858a43 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_cola_b_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_large_uncased_cola_b BertForSequenceClassification from EhsanAghazadeh +author: John Snow Labs +name: bert_large_uncased_cola_b +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_large_uncased_cola_b` is a English model originally trained by EhsanAghazadeh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_large_uncased_cola_b_en_5.1.4_3.4_1698204080875.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_large_uncased_cola_b_en_5.1.4_3.4_1698204080875.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_cola_b","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_cola_b","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_large_uncased_cola_b| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/EhsanAghazadeh/bert-large-uncased-CoLA_B \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_hoax_classifier_v1_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_hoax_classifier_v1_en.md new file mode 100644 index 00000000000000..d70f7e5053f647 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_hoax_classifier_v1_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_large_uncased_hoax_classifier_v1 BertForSequenceClassification from research-dump +author: John Snow Labs +name: bert_large_uncased_hoax_classifier_v1 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_large_uncased_hoax_classifier_v1` is a English model originally trained by research-dump. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_large_uncased_hoax_classifier_v1_en_5.1.4_3.4_1698229551553.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_large_uncased_hoax_classifier_v1_en_5.1.4_3.4_1698229551553.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_hoax_classifier_v1","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_hoax_classifier_v1","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_large_uncased_hoax_classifier_v1| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/research-dump/bert-large-uncased_hoax_classifier_v1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_mnli_ofirzaf_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_mnli_ofirzaf_en.md new file mode 100644 index 00000000000000..63886fb14ffb4e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_mnli_ofirzaf_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_large_uncased_mnli_ofirzaf BertForSequenceClassification from ofirzaf +author: John Snow Labs +name: bert_large_uncased_mnli_ofirzaf +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_large_uncased_mnli_ofirzaf` is a English model originally trained by ofirzaf. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_large_uncased_mnli_ofirzaf_en_5.1.4_3.4_1698239030775.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_large_uncased_mnli_ofirzaf_en_5.1.4_3.4_1698239030775.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_mnli_ofirzaf","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_mnli_ofirzaf","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_large_uncased_mnli_ofirzaf| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/ofirzaf/bert-large-uncased-mnli \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_16_13_30_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_16_13_30_en.md new file mode 100644 index 00000000000000..0f548ac7d8a7ca --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_16_13_30_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_large_uncased_sst_2_16_13_30 BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_large_uncased_sst_2_16_13_30 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_large_uncased_sst_2_16_13_30` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_large_uncased_sst_2_16_13_30_en_5.1.4_3.4_1698224647052.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_large_uncased_sst_2_16_13_30_en_5.1.4_3.4_1698224647052.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_sst_2_16_13_30","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_sst_2_16_13_30","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_large_uncased_sst_2_16_13_30| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/simonycl/bert-large-uncased-sst-2-16-13-30 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_16_13_smoothed_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_16_13_smoothed_en.md new file mode 100644 index 00000000000000..3f4e8dd0f028f6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_16_13_smoothed_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_large_uncased_sst_2_16_13_smoothed BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_large_uncased_sst_2_16_13_smoothed +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_large_uncased_sst_2_16_13_smoothed` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_large_uncased_sst_2_16_13_smoothed_en_5.1.4_3.4_1698220491868.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_large_uncased_sst_2_16_13_smoothed_en_5.1.4_3.4_1698220491868.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_sst_2_16_13_smoothed","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_sst_2_16_13_smoothed","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_large_uncased_sst_2_16_13_smoothed| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/simonycl/bert-large-uncased-sst-2-16-13-smoothed \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_32_13_30_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_32_13_30_en.md new file mode 100644 index 00000000000000..10834a73e981af --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_32_13_30_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_large_uncased_sst_2_32_13_30 BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_large_uncased_sst_2_32_13_30 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_large_uncased_sst_2_32_13_30` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_large_uncased_sst_2_32_13_30_en_5.1.4_3.4_1698225008323.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_large_uncased_sst_2_32_13_30_en_5.1.4_3.4_1698225008323.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_sst_2_32_13_30","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_sst_2_32_13_30","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_large_uncased_sst_2_32_13_30| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/simonycl/bert-large-uncased-sst-2-32-13-30 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_64_13_30_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_64_13_30_en.md new file mode 100644 index 00000000000000..7647d4ca3a2aab --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_large_uncased_sst_2_64_13_30_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_large_uncased_sst_2_64_13_30 BertForSequenceClassification from simonycl +author: John Snow Labs +name: bert_large_uncased_sst_2_64_13_30 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_large_uncased_sst_2_64_13_30` is a English model originally trained by simonycl. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_large_uncased_sst_2_64_13_30_en_5.1.4_3.4_1698226238586.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_large_uncased_sst_2_64_13_30_en_5.1.4_3.4_1698226238586.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_sst_2_64_13_30","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_large_uncased_sst_2_64_13_30","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_large_uncased_sst_2_64_13_30| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/simonycl/bert-large-uncased-sst-2-64-13-30 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_mnli_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_mnli_en.md new file mode 100644 index 00000000000000..c86eb14f202c19 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_mnli_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_mini_finetuned_mnli BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_mini_finetuned_mnli +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_mini_finetuned_mnli` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_mnli_en_5.1.4_3.4_1698222045987.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_mnli_en_5.1.4_3.4_1698222045987.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_mnli","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_mnli","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_mini_finetuned_mnli| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|42.1 MB| + +## References + +https://huggingface.co/M-FAC/bert-mini-finetuned-mnli \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_mrpc_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_mrpc_en.md new file mode 100644 index 00000000000000..4d6737a21da254 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_mrpc_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_mini_finetuned_mrpc BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_mini_finetuned_mrpc +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_mini_finetuned_mrpc` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_mrpc_en_5.1.4_3.4_1698222142012.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_mrpc_en_5.1.4_3.4_1698222142012.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_mrpc","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_mrpc","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_mini_finetuned_mrpc| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|42.1 MB| + +## References + +https://huggingface.co/M-FAC/bert-mini-finetuned-mrpc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_qnli_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_qnli_en.md new file mode 100644 index 00000000000000..06edc3f29f8485 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_qnli_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_mini_finetuned_qnli BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_mini_finetuned_qnli +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_mini_finetuned_qnli` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_qnli_en_5.1.4_3.4_1698222259511.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_qnli_en_5.1.4_3.4_1698222259511.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_qnli","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_qnli","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_mini_finetuned_qnli| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|42.1 MB| + +## References + +https://huggingface.co/M-FAC/bert-mini-finetuned-qnli \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_qqp_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_qqp_en.md new file mode 100644 index 00000000000000..7dc7272d8455d0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_qqp_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_mini_finetuned_qqp BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_mini_finetuned_qqp +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_mini_finetuned_qqp` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_qqp_en_5.1.4_3.4_1698222353761.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_qqp_en_5.1.4_3.4_1698222353761.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_qqp","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_qqp","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_mini_finetuned_qqp| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|42.1 MB| + +## References + +https://huggingface.co/M-FAC/bert-mini-finetuned-qqp \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_sst2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_sst2_en.md new file mode 100644 index 00000000000000..5647461caea8d4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_sst2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_mini_finetuned_sst2 BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_mini_finetuned_sst2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_mini_finetuned_sst2` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_sst2_en_5.1.4_3.4_1698222448691.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_sst2_en_5.1.4_3.4_1698222448691.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_sst2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_sst2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_mini_finetuned_sst2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|42.1 MB| + +## References + +https://huggingface.co/M-FAC/bert-mini-finetuned-sst2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_stsb_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_stsb_en.md new file mode 100644 index 00000000000000..34b3b2d4bac057 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_mini_finetuned_stsb_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_mini_finetuned_stsb BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_mini_finetuned_stsb +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_mini_finetuned_stsb` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_stsb_en_5.1.4_3.4_1698222538855.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_mini_finetuned_stsb_en_5.1.4_3.4_1698222538855.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_stsb","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_mini_finetuned_stsb","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_mini_finetuned_stsb| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|42.1 MB| + +## References + +https://huggingface.co/M-FAC/bert-mini-finetuned-stsb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_mixed_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_mixed_en.md new file mode 100644 index 00000000000000..49aa9d877edc14 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_mixed_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_mixed BertForSequenceClassification from PravallikaMyneni +author: John Snow Labs +name: bert_mixed +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_mixed` is a English model originally trained by PravallikaMyneni. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_mixed_en_5.1.4_3.4_1698222545171.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_mixed_en_5.1.4_3.4_1698222545171.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_mixed","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_mixed","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_mixed| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.9 MB| + +## References + +https://huggingface.co/PravallikaMyneni/bert_mixed \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_pre_doc_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_pre_doc_en.md new file mode 100644 index 00000000000000..75e5c6f1d1b618 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_pre_doc_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_pre_doc BertForSequenceClassification from LilaBoualili +author: John Snow Labs +name: bert_pre_doc +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_pre_doc` is a English model originally trained by LilaBoualili. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_pre_doc_en_5.1.4_3.4_1698220828401.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_pre_doc_en_5.1.4_3.4_1698220828401.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_pre_doc","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_pre_doc","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_pre_doc| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.5 MB| + +## References + +https://huggingface.co/LilaBoualili/bert-pre-doc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_pre_pair_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_pre_pair_en.md new file mode 100644 index 00000000000000..8c09fb2a1ae7e0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_pre_pair_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_pre_pair BertForSequenceClassification from LilaBoualili +author: John Snow Labs +name: bert_pre_pair +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_pre_pair` is a English model originally trained by LilaBoualili. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_pre_pair_en_5.1.4_3.4_1698221017879.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_pre_pair_en_5.1.4_3.4_1698221017879.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_pre_pair","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_pre_pair","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_pre_pair| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.5 MB| + +## References + +https://huggingface.co/LilaBoualili/bert-pre-pair \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sdg_french_fr.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sdg_french_fr.md new file mode 100644 index 00000000000000..ada1dbaeb13105 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sdg_french_fr.md @@ -0,0 +1,97 @@ +--- +layout: model +title: French bert_sdg_french BertForSequenceClassification from ilovebots +author: John Snow Labs +name: bert_sdg_french +date: 2023-10-25 +tags: [bert, fr, open_source, sequence_classification, onnx] +task: Text Classification +language: fr +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_sdg_french` is a French model originally trained by ilovebots. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sdg_french_fr_5.1.4_3.4_1698214647394.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sdg_french_fr_5.1.4_3.4_1698214647394.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sdg_french","fr")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sdg_french","fr") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sdg_french| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|fr| +|Size:|414.6 MB| + +## References + +https://huggingface.co/ilovebots/bert-sdg-french \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sentence_classifier_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sentence_classifier_en.md new file mode 100644 index 00000000000000..611b1a83e0f076 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sentence_classifier_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_sentence_classifier BertForSequenceClassification from Paleontolog +author: John Snow Labs +name: bert_sentence_classifier +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_sentence_classifier` is a English model originally trained by Paleontolog. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sentence_classifier_en_5.1.4_3.4_1698242352864.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sentence_classifier_en_5.1.4_3.4_1698242352864.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sentence_classifier","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sentence_classifier","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sentence_classifier| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|667.3 MB| + +## References + +https://huggingface.co/Paleontolog/bert_sentence_classifier \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sequce_classifier_paraphrase_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sequce_classifier_paraphrase_en.md new file mode 100644 index 00000000000000..01140afc54eaa6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sequce_classifier_paraphrase_en.md @@ -0,0 +1,100 @@ +--- +layout: model +title: English BertForSequenceClassification Cased model (from Prompsit) +author: John Snow Labs +name: bert_sequce_classifier_paraphrase +date: 2023-10-25 +tags: [en, open_source, bert, sequence_classification, ner, onnx] +task: Named Entity Recognition +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `paraphrase-bert-en` is a English model originally trained by `Prompsit`. + +## Predicted Entities + +`Not Paraphrase`, `Paraphrase` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sequce_classifier_paraphrase_en_5.1.4_3.4_1698231258424.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sequce_classifier_paraphrase_en_5.1.4_3.4_1698231258424.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") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequce_classifier_paraphrase","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).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 sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequce_classifier_paraphrase","en") + .setInputCols(Array("document", "token")) + .setOutputCol("ner") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sequce_classifier_paraphrase| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[ner]| +|Language:|en| +|Size:|409.4 MB| +|Case sensitive:|true| +|Max sentence length:|128| + +## References + +References + +- https://huggingface.co/Prompsit/paraphrase-bert-en \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_base_uncased_finetuned_surveyclassification_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_base_uncased_finetuned_surveyclassification_en.md new file mode 100644 index 00000000000000..49d58adbd7092c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_base_uncased_finetuned_surveyclassification_en.md @@ -0,0 +1,100 @@ +--- +layout: model +title: English BertForSequenceClassification Base Uncased model (from Jorgeutd) +author: John Snow Labs +name: bert_sequence_classifier_base_uncased_finetuned_surveyclassification +date: 2023-10-25 +tags: [en, open_source, bert, sequence_classification, ner, onnx] +task: Named Entity Recognition +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-uncased-finetuned-surveyclassification` is a English model originally trained by `Jorgeutd`. + +## Predicted Entities + +`positive`, `neutral`, `negative` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_base_uncased_finetuned_surveyclassification_en_5.1.4_3.4_1698219648617.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_base_uncased_finetuned_surveyclassification_en_5.1.4_3.4_1698219648617.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") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_base_uncased_finetuned_surveyclassification","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).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 sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_base_uncased_finetuned_surveyclassification","en") + .setInputCols(Array("document", "token")) + .setOutputCol("ner") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sequence_classifier_base_uncased_finetuned_surveyclassification| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[ner]| +|Language:|en| +|Size:|409.4 MB| +|Case sensitive:|true| +|Max sentence length:|128| + +## References + +References + +- https://huggingface.co/Jorgeutd/bert-base-uncased-finetuned-surveyclassification \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_base_uncased_sst2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_base_uncased_sst2_en.md new file mode 100644 index 00000000000000..bf377d771b78ab --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_base_uncased_sst2_en.md @@ -0,0 +1,101 @@ +--- +layout: model +title: English BertForSequenceClassification Base Uncased model (from JeremiahZ) +author: John Snow Labs +name: bert_sequence_classifier_base_uncased_sst2 +date: 2023-10-25 +tags: [en, open_source, bert, sequence_classification, ner, onnx] +task: Named Entity Recognition +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-uncased-sst2` is a English model originally trained by `JeremiahZ`. + +## Predicted Entities + +`positive`, `negative` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_base_uncased_sst2_en_5.1.4_3.4_1698208956258.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_base_uncased_sst2_en_5.1.4_3.4_1698208956258.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") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_base_uncased_sst2","en") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).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 sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_base_uncased_sst2","en") + .setInputCols(Array("document", "token")) + .setOutputCol("ner") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sequence_classifier_base_uncased_sst2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[ner]| +|Language:|en| +|Size:|409.4 MB| +|Case sensitive:|true| +|Max sentence length:|128| + +## References + +References + +- https://huggingface.co/JeremiahZ/bert-base-uncased-sst2 +- https://paperswithcode.com/sota?task=Text+Classification&dataset=GLUE+SST2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_dehate_mono_portugese_pt.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_dehate_mono_portugese_pt.md new file mode 100644 index 00000000000000..5d054e173420dd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_dehate_mono_portugese_pt.md @@ -0,0 +1,102 @@ +--- +layout: model +title: Portuguese BertForSequenceClassification Cased model (from Hate-speech-CNERG) +author: John Snow Labs +name: bert_sequence_classifier_dehate_mono_portugese +date: 2023-10-25 +tags: [pt, open_source, bert, sequence_classification, ner, onnx] +task: Named Entity Recognition +language: pt +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `dehatebert-mono-portugese` is a Portuguese model originally trained by `Hate-speech-CNERG`. + +## Predicted Entities + +`NON_HATE`, `HATE` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_dehate_mono_portugese_pt_5.1.4_3.4_1698208710232.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_dehate_mono_portugese_pt_5.1.4_3.4_1698208710232.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") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_dehate_mono_portugese","pt") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).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 sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_dehate_mono_portugese","pt") + .setInputCols(Array("document", "token")) + .setOutputCol("ner") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sequence_classifier_dehate_mono_portugese| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[ner]| +|Language:|pt| +|Size:|627.7 MB| +|Case sensitive:|true| +|Max sentence length:|128| + +## References + +References + +- https://huggingface.co/Hate-speech-CNERG/dehatebert-mono-portugese +- https://github.com/punyajoy/DE-LIMIT +- https://arxiv.org/abs/2004.06465 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_paraphrase_pt.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_paraphrase_pt.md new file mode 100644 index 00000000000000..c5ff6d7364ff75 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_paraphrase_pt.md @@ -0,0 +1,100 @@ +--- +layout: model +title: Portuguese BertForSequenceClassification Cased model (from Prompsit) +author: John Snow Labs +name: bert_sequence_classifier_paraphrase +date: 2023-10-25 +tags: [pt, open_source, bert, sequence_classification, ner, onnx] +task: Named Entity Recognition +language: pt +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `paraphrase-bert-pt` is a Portuguese model originally trained by `Prompsit`. + +## Predicted Entities + +`Not Paraphrase`, `Paraphrase` + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_paraphrase_pt_5.1.4_3.4_1698232661863.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_paraphrase_pt_5.1.4_3.4_1698232661863.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") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_paraphrase","pt") \ + .setInputCols(["document", "token"]) \ + .setOutputCol("class") + +pipeline = Pipeline(stages=[documentAssembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).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 sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_paraphrase","pt") + .setInputCols(Array("document", "token")) + .setOutputCol("ner") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sequence_classifier_paraphrase| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[document, token]| +|Output Labels:|[ner]| +|Language:|pt| +|Size:|408.2 MB| +|Case sensitive:|true| +|Max sentence length:|128| + +## References + +References + +- https://huggingface.co/Prompsit/paraphrase-bert-pt \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi_fa.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi_fa.md new file mode 100644 index 00000000000000..9feda5ef5fc54a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi_fa.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Persian bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi BertForSequenceClassification from HooshvareLab +author: John Snow Labs +name: bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi +date: 2023-10-25 +tags: [bert, fa, open_source, sequence_classification, onnx] +task: Text Classification +language: fa +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi` is a Persian model originally trained by HooshvareLab. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi_fa_5.1.4_3.4_1698210004394.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi_fa_5.1.4_3.4_1698210004394.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi","fa")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi","fa") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sequence_classifier_persian_farsi_base_uncased_sentiment_deepsentipers_multi| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|fa| +|Size:|608.7 MB| + +## References + +https://huggingface.co/HooshvareLab/bert-fa-base-uncased-sentiment-deepsentipers-multi \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala_fa.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala_fa.md new file mode 100644 index 00000000000000..343b06b8e5ed38 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala_fa.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Persian bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala BertForSequenceClassification from HooshvareLab +author: John Snow Labs +name: bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala +date: 2023-10-25 +tags: [bert, fa, open_source, sequence_classification, onnx] +task: Text Classification +language: fa +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala` is a Persian model originally trained by HooshvareLab. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala_fa_5.1.4_3.4_1698210264996.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala_fa_5.1.4_3.4_1698210264996.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala","fa")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala","fa") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sequence_classifier_persian_farsi_base_uncased_sentiment_digikala| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|fa| +|Size:|608.7 MB| + +## References + +https://huggingface.co/HooshvareLab/bert-fa-base-uncased-sentiment-digikala \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood_fa.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood_fa.md new file mode 100644 index 00000000000000..85056d89c3ccd6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood_fa.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Persian bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood BertForSequenceClassification from HooshvareLab +author: John Snow Labs +name: bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood +date: 2023-10-25 +tags: [bert, fa, open_source, sequence_classification, onnx] +task: Text Classification +language: fa +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood` is a Persian model originally trained by HooshvareLab. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood_fa_5.1.4_3.4_1698210508316.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood_fa_5.1.4_3.4_1698210508316.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood","fa")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood","fa") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sequence_classifier_persian_farsi_base_uncased_sentiment_snappfood| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|fa| +|Size:|608.7 MB| + +## References + +https://huggingface.co/HooshvareLab/bert-fa-base-uncased-sentiment-snappfood \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sim_doc_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sim_doc_en.md new file mode 100644 index 00000000000000..b597749fd4d9d9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sim_doc_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_sim_doc BertForSequenceClassification from LilaBoualili +author: John Snow Labs +name: bert_sim_doc +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_sim_doc` is a English model originally trained by LilaBoualili. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sim_doc_en_5.1.4_3.4_1698221193643.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sim_doc_en_5.1.4_3.4_1698221193643.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sim_doc","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sim_doc","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sim_doc| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/LilaBoualili/bert-sim-doc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_sim_pair_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_sim_pair_en.md new file mode 100644 index 00000000000000..c3ebb2668186f8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_sim_pair_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_sim_pair BertForSequenceClassification from LilaBoualili +author: John Snow Labs +name: bert_sim_pair +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_sim_pair` is a English model originally trained by LilaBoualili. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_sim_pair_en_5.1.4_3.4_1698221374777.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_sim_pair_en_5.1.4_3.4_1698221374777.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_sim_pair","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sim_pair","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_sim_pair| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/LilaBoualili/bert-sim-pair \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_mnli_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_mnli_en.md new file mode 100644 index 00000000000000..4ce35b5fb49fc7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_mnli_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_tiny_finetuned_mnli BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_tiny_finetuned_mnli +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_tiny_finetuned_mnli` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_mnli_en_5.1.4_3.4_1698222635613.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_mnli_en_5.1.4_3.4_1698222635613.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_mnli","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_mnli","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_tiny_finetuned_mnli| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|16.7 MB| + +## References + +https://huggingface.co/M-FAC/bert-tiny-finetuned-mnli \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_mrpc_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_mrpc_en.md new file mode 100644 index 00000000000000..bb433413792c4c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_mrpc_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_tiny_finetuned_mrpc BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_tiny_finetuned_mrpc +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_tiny_finetuned_mrpc` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_mrpc_en_5.1.4_3.4_1698222721542.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_mrpc_en_5.1.4_3.4_1698222721542.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_mrpc","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_mrpc","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_tiny_finetuned_mrpc| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|16.7 MB| + +## References + +https://huggingface.co/M-FAC/bert-tiny-finetuned-mrpc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_qnli_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_qnli_en.md new file mode 100644 index 00000000000000..4ea066c989469b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_qnli_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_tiny_finetuned_qnli BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_tiny_finetuned_qnli +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_tiny_finetuned_qnli` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_qnli_en_5.1.4_3.4_1698222815267.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_qnli_en_5.1.4_3.4_1698222815267.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_qnli","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_qnli","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_tiny_finetuned_qnli| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|16.7 MB| + +## References + +https://huggingface.co/M-FAC/bert-tiny-finetuned-qnli \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_qqp_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_qqp_en.md new file mode 100644 index 00000000000000..ffe2e048cb4561 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_qqp_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_tiny_finetuned_qqp BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_tiny_finetuned_qqp +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_tiny_finetuned_qqp` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_qqp_en_5.1.4_3.4_1698222915759.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_qqp_en_5.1.4_3.4_1698222915759.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_qqp","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_qqp","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_tiny_finetuned_qqp| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|16.7 MB| + +## References + +https://huggingface.co/M-FAC/bert-tiny-finetuned-qqp \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_sst2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_sst2_en.md new file mode 100644 index 00000000000000..119e41dac1f850 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_sst2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_tiny_finetuned_sst2 BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_tiny_finetuned_sst2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_tiny_finetuned_sst2` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_sst2_en_5.1.4_3.4_1698223010239.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_sst2_en_5.1.4_3.4_1698223010239.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_sst2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_sst2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_tiny_finetuned_sst2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|16.7 MB| + +## References + +https://huggingface.co/M-FAC/bert-tiny-finetuned-sst2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_stsb_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_stsb_en.md new file mode 100644 index 00000000000000..b625afd2dd6355 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_tiny_finetuned_stsb_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_tiny_finetuned_stsb BertForSequenceClassification from M-FAC +author: John Snow Labs +name: bert_tiny_finetuned_stsb +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_tiny_finetuned_stsb` is a English model originally trained by M-FAC. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_stsb_en_5.1.4_3.4_1698223101321.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_tiny_finetuned_stsb_en_5.1.4_3.4_1698223101321.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_stsb","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_tiny_finetuned_stsb","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_tiny_finetuned_stsb| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|16.7 MB| + +## References + +https://huggingface.co/M-FAC/bert-tiny-finetuned-stsb \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_tweets_semeval_unclean_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_tweets_semeval_unclean_en.md new file mode 100644 index 00000000000000..797d04bc672bb2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_tweets_semeval_unclean_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_tweets_semeval_unclean BertForSequenceClassification from DoyyingFace +author: John Snow Labs +name: bert_tweets_semeval_unclean +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_tweets_semeval_unclean` is a English model originally trained by DoyyingFace. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_tweets_semeval_unclean_en_5.1.4_3.4_1698201555184.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_tweets_semeval_unclean_en_5.1.4_3.4_1698201555184.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_tweets_semeval_unclean","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_tweets_semeval_unclean","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_tweets_semeval_unclean| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/DoyyingFace/bert-tweets-semeval-unclean \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_vanilla_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_vanilla_en.md new file mode 100644 index 00000000000000..b0cec13a6b38c5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_vanilla_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_vanilla BertForSequenceClassification from LilaBoualili +author: John Snow Labs +name: bert_vanilla +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_vanilla` is a English model originally trained by LilaBoualili. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_vanilla_en_5.1.4_3.4_1698221552184.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_vanilla_en_5.1.4_3.4_1698221552184.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_vanilla","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_vanilla","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_vanilla| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/LilaBoualili/bert-vanilla \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_wiki_comments_finetuned_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_wiki_comments_finetuned_en.md new file mode 100644 index 00000000000000..255d344248db6b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_wiki_comments_finetuned_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_wiki_comments_finetuned BertForSequenceClassification from DoyyingFace +author: John Snow Labs +name: bert_wiki_comments_finetuned +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_wiki_comments_finetuned` is a English model originally trained by DoyyingFace. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_wiki_comments_finetuned_en_5.1.4_3.4_1698201749015.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_wiki_comments_finetuned_en_5.1.4_3.4_1698201749015.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_wiki_comments_finetuned","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_wiki_comments_finetuned","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_wiki_comments_finetuned| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/DoyyingFace/bert-wiki-comments-finetuned \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bert_wikipedia_sst2_en.md b/docs/_posts/ahmedlone127/2023-10-25-bert_wikipedia_sst2_en.md new file mode 100644 index 00000000000000..0decb892f3ea53 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bert_wikipedia_sst2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bert_wikipedia_sst2 BertForSequenceClassification from deepesh0x +author: John Snow Labs +name: bert_wikipedia_sst2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bert_wikipedia_sst2` is a English model originally trained by deepesh0x. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bert_wikipedia_sst2_en_5.1.4_3.4_1698211274392.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_wikipedia_sst2_en_5.1.4_3.4_1698211274392.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bert_wikipedia_sst2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bert_wikipedia_sst2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bert_wikipedia_sst2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/deepesh0x/bert_wikipedia_sst2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-bertabaporu_portuguese_irony_en.md b/docs/_posts/ahmedlone127/2023-10-25-bertabaporu_portuguese_irony_en.md new file mode 100644 index 00000000000000..9f393d39e88ebc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-bertabaporu_portuguese_irony_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English bertabaporu_portuguese_irony BertForSequenceClassification from pysentimiento +author: John Snow Labs +name: bertabaporu_portuguese_irony +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`bertabaporu_portuguese_irony` is a English model originally trained by pysentimiento. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/bertabaporu_portuguese_irony_en_5.1.4_3.4_1698227283769.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bertabaporu_portuguese_irony_en_5.1.4_3.4_1698227283769.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("bertabaporu_portuguese_irony","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("bertabaporu_portuguese_irony","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|bertabaporu_portuguese_irony| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|507.0 MB| + +## References + +https://huggingface.co/pysentimiento/bertabaporu-pt-irony \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-biobert_finetuned_genetic_mutation_en.md b/docs/_posts/ahmedlone127/2023-10-25-biobert_finetuned_genetic_mutation_en.md new file mode 100644 index 00000000000000..9a1ce98a172d31 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-biobert_finetuned_genetic_mutation_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English biobert_finetuned_genetic_mutation BertForSequenceClassification from wahdan99 +author: John Snow Labs +name: biobert_finetuned_genetic_mutation +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`biobert_finetuned_genetic_mutation` is a English model originally trained by wahdan99. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/biobert_finetuned_genetic_mutation_en_5.1.4_3.4_1698224837394.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/biobert_finetuned_genetic_mutation_en_5.1.4_3.4_1698224837394.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("biobert_finetuned_genetic_mutation","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("biobert_finetuned_genetic_mutation","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|biobert_finetuned_genetic_mutation| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.3 MB| + +## References + +https://huggingface.co/wahdan99/biobert-finetuned-genetic-mutation \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-boss_sentiment_bert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-10-25-boss_sentiment_bert_base_uncased_en.md new file mode 100644 index 00000000000000..13522eff0e11e1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-boss_sentiment_bert_base_uncased_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English boss_sentiment_bert_base_uncased BertForSequenceClassification from Kyle1668 +author: John Snow Labs +name: boss_sentiment_bert_base_uncased +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`boss_sentiment_bert_base_uncased` is a English model originally trained by Kyle1668. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/boss_sentiment_bert_base_uncased_en_5.1.4_3.4_1698221348012.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/boss_sentiment_bert_base_uncased_en_5.1.4_3.4_1698221348012.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("boss_sentiment_bert_base_uncased","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("boss_sentiment_bert_base_uncased","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|boss_sentiment_bert_base_uncased| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Kyle1668/boss-sentiment-bert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-boss_toxicity_bert_base_uncased_en.md b/docs/_posts/ahmedlone127/2023-10-25-boss_toxicity_bert_base_uncased_en.md new file mode 100644 index 00000000000000..376157fbf627b7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-boss_toxicity_bert_base_uncased_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English boss_toxicity_bert_base_uncased BertForSequenceClassification from Kyle1668 +author: John Snow Labs +name: boss_toxicity_bert_base_uncased +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`boss_toxicity_bert_base_uncased` is a English model originally trained by Kyle1668. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/boss_toxicity_bert_base_uncased_en_5.1.4_3.4_1698221527242.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/boss_toxicity_bert_base_uncased_en_5.1.4_3.4_1698221527242.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("boss_toxicity_bert_base_uncased","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("boss_toxicity_bert_base_uncased","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|boss_toxicity_bert_base_uncased| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Kyle1668/boss-toxicity-bert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-chinese_roberta_wwm_ext_finetuned_binary_en.md b/docs/_posts/ahmedlone127/2023-10-25-chinese_roberta_wwm_ext_finetuned_binary_en.md new file mode 100644 index 00000000000000..c4d3f7d814634f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-chinese_roberta_wwm_ext_finetuned_binary_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English chinese_roberta_wwm_ext_finetuned_binary BertForSequenceClassification from Raychanan +author: John Snow Labs +name: chinese_roberta_wwm_ext_finetuned_binary +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`chinese_roberta_wwm_ext_finetuned_binary` is a English model originally trained by Raychanan. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/chinese_roberta_wwm_ext_finetuned_binary_en_5.1.4_3.4_1698235230260.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/chinese_roberta_wwm_ext_finetuned_binary_en_5.1.4_3.4_1698235230260.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("chinese_roberta_wwm_ext_finetuned_binary","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("chinese_roberta_wwm_ext_finetuned_binary","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|chinese_roberta_wwm_ext_finetuned_binary| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.2 MB| + +## References + +https://huggingface.co/Raychanan/chinese-roberta-wwm-ext-FineTuned-Binary \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_1_4_2e_05_0_01_en.md b/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_1_4_2e_05_0_01_en.md new file mode 100644 index 00000000000000..266876cec82bdd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_1_4_2e_05_0_01_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English covid_twitter_bert_v2_1_4_2e_05_0_01 BertForSequenceClassification from JerryYanJiang +author: John Snow Labs +name: covid_twitter_bert_v2_1_4_2e_05_0_01 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`covid_twitter_bert_v2_1_4_2e_05_0_01` is a English model originally trained by JerryYanJiang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/covid_twitter_bert_v2_1_4_2e_05_0_01_en_5.1.4_3.4_1698219195720.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/covid_twitter_bert_v2_1_4_2e_05_0_01_en_5.1.4_3.4_1698219195720.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("covid_twitter_bert_v2_1_4_2e_05_0_01","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("covid_twitter_bert_v2_1_4_2e_05_0_01","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|covid_twitter_bert_v2_1_4_2e_05_0_01| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/JerryYanJiang/covid-twitter-bert-v2_1_4_2e-05_0.01 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01_en.md b/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01_en.md new file mode 100644 index 00000000000000..5376352c5b5c55 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01 BertForSequenceClassification from JerryYanJiang +author: John Snow Labs +name: covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01` is a English model originally trained by JerryYanJiang. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01_en_5.1.4_3.4_1698217732233.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01_en_5.1.4_3.4_1698217732233.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|covid_twitter_bert_v2_epoch3_batch4_lr2e_05_w0_01| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/JerryYanJiang/covid-twitter-bert-v2_epoch3_batch4_lr2e-05_w0.01 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera_en.md b/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera_en.md new file mode 100644 index 00000000000000..64d2a043d42408 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera BertForSequenceClassification from liyijing024 +author: John Snow Labs +name: covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera` is a English model originally trained by liyijing024. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera_en_5.1.4_3.4_1698237356534.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera_en_5.1.4_3.4_1698237356534.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|covid_twitter_bert_v2_mnli_nli_sts_crossencoder_covid_hera| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/liyijing024/covid-twitter-bert-v2-mnli-NLI-STS-CrossEncoder-Covid-HeRA \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-deprem_berturk_binary_tr.md b/docs/_posts/ahmedlone127/2023-10-25-deprem_berturk_binary_tr.md new file mode 100644 index 00000000000000..93a6c5af8e4e43 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-deprem_berturk_binary_tr.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Turkish deprem_berturk_binary BertForSequenceClassification from ctoraman +author: John Snow Labs +name: deprem_berturk_binary +date: 2023-10-25 +tags: [bert, tr, open_source, sequence_classification, onnx] +task: Text Classification +language: tr +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`deprem_berturk_binary` is a Turkish model originally trained by ctoraman. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/deprem_berturk_binary_tr_5.1.4_3.4_1698218881162.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/deprem_berturk_binary_tr_5.1.4_3.4_1698218881162.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("deprem_berturk_binary","tr")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("deprem_berturk_binary","tr") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|deprem_berturk_binary| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|tr| +|Size:|414.5 MB| + +## References + +https://huggingface.co/ctoraman/deprem-berturk-binary \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-dk_emotion_bert_2_en.md b/docs/_posts/ahmedlone127/2023-10-25-dk_emotion_bert_2_en.md new file mode 100644 index 00000000000000..4953bc34c7f514 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-dk_emotion_bert_2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English dk_emotion_bert_2 BertForSequenceClassification from Only-Mike +author: John Snow Labs +name: dk_emotion_bert_2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`dk_emotion_bert_2` is a English model originally trained by Only-Mike. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/dk_emotion_bert_2_en_5.1.4_3.4_1698223071802.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/dk_emotion_bert_2_en_5.1.4_3.4_1698223071802.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("dk_emotion_bert_2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("dk_emotion_bert_2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|dk_emotion_bert_2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|414.6 MB| + +## References + +https://huggingface.co/Only-Mike/dk_emotion_bert_2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-dk_emotion_bert_class_en.md b/docs/_posts/ahmedlone127/2023-10-25-dk_emotion_bert_class_en.md new file mode 100644 index 00000000000000..5bb80989303491 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-dk_emotion_bert_class_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English dk_emotion_bert_class BertForSequenceClassification from Korsholm22 +author: John Snow Labs +name: dk_emotion_bert_class +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`dk_emotion_bert_class` is a English model originally trained by Korsholm22. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/dk_emotion_bert_class_en_5.1.4_3.4_1698222898858.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/dk_emotion_bert_class_en_5.1.4_3.4_1698222898858.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("dk_emotion_bert_class","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("dk_emotion_bert_class","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|dk_emotion_bert_class| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|414.6 MB| + +## References + +https://huggingface.co/Korsholm22/dk_emotion_bert_class \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-esg_bert_sector_classifier_en.md b/docs/_posts/ahmedlone127/2023-10-25-esg_bert_sector_classifier_en.md new file mode 100644 index 00000000000000..9d2530e3eb06d4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-esg_bert_sector_classifier_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English esg_bert_sector_classifier BertForSequenceClassification from ppsingh +author: John Snow Labs +name: esg_bert_sector_classifier +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`esg_bert_sector_classifier` is a English model originally trained by ppsingh. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/esg_bert_sector_classifier_en_5.1.4_3.4_1698229025440.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/esg_bert_sector_classifier_en_5.1.4_3.4_1698229025440.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("esg_bert_sector_classifier","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("esg_bert_sector_classifier","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|esg_bert_sector_classifier| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.8 MB| + +## References + +https://huggingface.co/ppsingh/esg-bert-sector-classifier \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-finbert_finetuned_fg_single_sentence_news_weighted_en.md b/docs/_posts/ahmedlone127/2023-10-25-finbert_finetuned_fg_single_sentence_news_weighted_en.md new file mode 100644 index 00000000000000..5e6e199c7e098c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-finbert_finetuned_fg_single_sentence_news_weighted_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English finbert_finetuned_fg_single_sentence_news_weighted BertForSequenceClassification from lucaordronneau +author: John Snow Labs +name: finbert_finetuned_fg_single_sentence_news_weighted +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`finbert_finetuned_fg_single_sentence_news_weighted` is a English model originally trained by lucaordronneau. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/finbert_finetuned_fg_single_sentence_news_weighted_en_5.1.4_3.4_1698241050659.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/finbert_finetuned_fg_single_sentence_news_weighted_en_5.1.4_3.4_1698241050659.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("finbert_finetuned_fg_single_sentence_news_weighted","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("finbert_finetuned_fg_single_sentence_news_weighted","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|finbert_finetuned_fg_single_sentence_news_weighted| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/lucaordronneau/finbert-finetuned-FG-SINGLE_SENTENCE-NEWS-WEIGHTED \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-finbert_fls_en.md b/docs/_posts/ahmedlone127/2023-10-25-finbert_fls_en.md new file mode 100644 index 00000000000000..db3949ce9f2f7a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-finbert_fls_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English finbert_fls BertForSequenceClassification from yiyanghkust +author: John Snow Labs +name: finbert_fls +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`finbert_fls` is a English model originally trained by yiyanghkust. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/finbert_fls_en_5.1.4_3.4_1698245276476.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/finbert_fls_en_5.1.4_3.4_1698245276476.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("finbert_fls","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("finbert_fls","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|finbert_fls| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|411.6 MB| + +## References + +https://huggingface.co/yiyanghkust/finbert-fls \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji_en.md new file mode 100644 index 00000000000000..3980e5051c15b1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji BertForSequenceClassification from afaji +author: John Snow Labs +name: fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji` is a English model originally trained by afaji. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji_en_5.1.4_3.4_1698221048030.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji_en_5.1.4_3.4_1698221048030.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_augmented_with_indobert_base_uncased_afaji| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|413.9 MB| + +## References + +https://huggingface.co/afaji/fine-tuned-IndoNLI-Augmented-with-indobert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001_en.md new file mode 100644 index 00000000000000..99fe6e43b50a22 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001 BertForSequenceClassification from muhammadravi251001 +author: John Snow Labs +name: fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001` is a English model originally trained by muhammadravi251001. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001_en_5.1.4_3.4_1698225941984.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001_en_5.1.4_3.4_1698225941984.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_augmented_with_indobert_base_uncased_muhammadravi251001| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|413.9 MB| + +## References + +https://huggingface.co/muhammadravi251001/fine-tuned-IndoNLI-Augmented-with-indobert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_large_p2_afaji_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_large_p2_afaji_en.md new file mode 100644 index 00000000000000..621d35e533a7d6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_large_p2_afaji_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_augmented_with_indobert_large_p2_afaji BertForSequenceClassification from afaji +author: John Snow Labs +name: fine_tuned_indonli_augmented_with_indobert_large_p2_afaji +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_augmented_with_indobert_large_p2_afaji` is a English model originally trained by afaji. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_augmented_with_indobert_large_p2_afaji_en_5.1.4_3.4_1698220859599.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_augmented_with_indobert_large_p2_afaji_en_5.1.4_3.4_1698220859599.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_augmented_with_indobert_large_p2_afaji","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_augmented_with_indobert_large_p2_afaji","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_augmented_with_indobert_large_p2_afaji| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/afaji/fine-tuned-IndoNLI-Augmented-with-indobert-large-p2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001_en.md new file mode 100644 index 00000000000000..94bba1b2d3c5b6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001 BertForSequenceClassification from muhammadravi251001 +author: John Snow Labs +name: fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001` is a English model originally trained by muhammadravi251001. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001_en_5.1.4_3.4_1698223677212.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001_en_5.1.4_3.4_1698223677212.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_augmented_with_indobert_large_p2_muhammadravi251001| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/muhammadravi251001/fine-tuned-IndoNLI-Augmented-with-indobert-large-p2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_base_uncased_afaji_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_base_uncased_afaji_en.md new file mode 100644 index 00000000000000..c8a49a6f970488 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_base_uncased_afaji_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_basic_with_indobert_base_uncased_afaji BertForSequenceClassification from afaji +author: John Snow Labs +name: fine_tuned_indonli_basic_with_indobert_base_uncased_afaji +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_basic_with_indobert_base_uncased_afaji` is a English model originally trained by afaji. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_basic_with_indobert_base_uncased_afaji_en_5.1.4_3.4_1698219271386.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_basic_with_indobert_base_uncased_afaji_en_5.1.4_3.4_1698219271386.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_basic_with_indobert_base_uncased_afaji","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_basic_with_indobert_base_uncased_afaji","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_basic_with_indobert_base_uncased_afaji| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|413.9 MB| + +## References + +https://huggingface.co/afaji/fine-tuned-IndoNLI-Basic-with-indobert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001_en.md new file mode 100644 index 00000000000000..ff7efc7423853a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001 BertForSequenceClassification from muhammadravi251001 +author: John Snow Labs +name: fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001` is a English model originally trained by muhammadravi251001. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001_en_5.1.4_3.4_1698225044555.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001_en_5.1.4_3.4_1698225044555.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_basic_with_indobert_base_uncased_muhammadravi251001| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|413.9 MB| + +## References + +https://huggingface.co/muhammadravi251001/fine-tuned-IndoNLI-Basic-with-indobert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_large_p2_afaji_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_large_p2_afaji_en.md new file mode 100644 index 00000000000000..60ae6ef7cfe365 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_large_p2_afaji_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_basic_with_indobert_large_p2_afaji BertForSequenceClassification from afaji +author: John Snow Labs +name: fine_tuned_indonli_basic_with_indobert_large_p2_afaji +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_basic_with_indobert_large_p2_afaji` is a English model originally trained by afaji. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_basic_with_indobert_large_p2_afaji_en_5.1.4_3.4_1698219934268.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_basic_with_indobert_large_p2_afaji_en_5.1.4_3.4_1698219934268.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_basic_with_indobert_large_p2_afaji","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_basic_with_indobert_large_p2_afaji","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_basic_with_indobert_large_p2_afaji| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/afaji/fine-tuned-IndoNLI-Basic-with-indobert-large-p2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001_en.md new file mode 100644 index 00000000000000..4fc489ec386c5c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001 BertForSequenceClassification from muhammadravi251001 +author: John Snow Labs +name: fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001` is a English model originally trained by muhammadravi251001. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001_en_5.1.4_3.4_1698224046216.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001_en_5.1.4_3.4_1698224046216.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_basic_with_indobert_large_p2_muhammadravi251001| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/muhammadravi251001/fine-tuned-IndoNLI-Basic-with-indobert-large-p2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_base_uncased_afaji_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_base_uncased_afaji_en.md new file mode 100644 index 00000000000000..b6bb021fec9193 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_base_uncased_afaji_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_translated_with_indobert_base_uncased_afaji BertForSequenceClassification from afaji +author: John Snow Labs +name: fine_tuned_indonli_translated_with_indobert_base_uncased_afaji +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_translated_with_indobert_base_uncased_afaji` is a English model originally trained by afaji. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_translated_with_indobert_base_uncased_afaji_en_5.1.4_3.4_1698219456786.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_translated_with_indobert_base_uncased_afaji_en_5.1.4_3.4_1698219456786.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_translated_with_indobert_base_uncased_afaji","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_translated_with_indobert_base_uncased_afaji","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_translated_with_indobert_base_uncased_afaji| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|413.9 MB| + +## References + +https://huggingface.co/afaji/fine-tuned-IndoNLI-Translated-with-indobert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001_en.md new file mode 100644 index 00000000000000..ef47c1fe1b46f2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001 BertForSequenceClassification from muhammadravi251001 +author: John Snow Labs +name: fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001` is a English model originally trained by muhammadravi251001. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001_en_5.1.4_3.4_1698219097750.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001_en_5.1.4_3.4_1698219097750.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_translated_with_indobert_base_uncased_muhammadravi251001| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|413.9 MB| + +## References + +https://huggingface.co/muhammadravi251001/fine-tuned-IndoNLI-Translated-with-indobert-base-uncased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_large_p2_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_large_p2_en.md new file mode 100644 index 00000000000000..37b51526c73bce --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_indonli_translated_with_indobert_large_p2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_indonli_translated_with_indobert_large_p2 BertForSequenceClassification from afaji +author: John Snow Labs +name: fine_tuned_indonli_translated_with_indobert_large_p2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_indonli_translated_with_indobert_large_p2` is a English model originally trained by afaji. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_translated_with_indobert_large_p2_en_5.1.4_3.4_1698220492900.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_indonli_translated_with_indobert_large_p2_en_5.1.4_3.4_1698220492900.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_translated_with_indobert_large_p2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_indonli_translated_with_indobert_large_p2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_indonli_translated_with_indobert_large_p2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/afaji/fine-tuned-IndoNLI-Translated-with-indobert-large-p2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_koreanindonli_kornli_with_bert_base_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_koreanindonli_kornli_with_bert_base_en.md new file mode 100644 index 00000000000000..c609724838520b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_koreanindonli_kornli_with_bert_base_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_koreanindonli_kornli_with_bert_base BertForSequenceClassification from muhammadravi251001 +author: John Snow Labs +name: fine_tuned_koreanindonli_kornli_with_bert_base +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_koreanindonli_kornli_with_bert_base` is a English model originally trained by muhammadravi251001. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_koreanindonli_kornli_with_bert_base_en_5.1.4_3.4_1698245173848.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_koreanindonli_kornli_with_bert_base_en_5.1.4_3.4_1698245173848.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_koreanindonli_kornli_with_bert_base","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_koreanindonli_kornli_with_bert_base","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_koreanindonli_kornli_with_bert_base| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|414.6 MB| + +## References + +https://huggingface.co/muhammadravi251001/fine-tuned-KoreanIndoNLI-KorNLI-with-bert-base \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_koreanindonli_kornli_with_bert_kor_base_en.md b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_koreanindonli_kornli_with_bert_kor_base_en.md new file mode 100644 index 00000000000000..afb80453f32e98 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-fine_tuned_koreanindonli_kornli_with_bert_kor_base_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English fine_tuned_koreanindonli_kornli_with_bert_kor_base BertForSequenceClassification from muhammadravi251001 +author: John Snow Labs +name: fine_tuned_koreanindonli_kornli_with_bert_kor_base +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`fine_tuned_koreanindonli_kornli_with_bert_kor_base` is a English model originally trained by muhammadravi251001. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/fine_tuned_koreanindonli_kornli_with_bert_kor_base_en_5.1.4_3.4_1698228339319.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/fine_tuned_koreanindonli_kornli_with_bert_kor_base_en_5.1.4_3.4_1698228339319.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_koreanindonli_kornli_with_bert_kor_base","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("fine_tuned_koreanindonli_kornli_with_bert_kor_base","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|fine_tuned_koreanindonli_kornli_with_bert_kor_base| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|443.4 MB| + +## References + +https://huggingface.co/muhammadravi251001/fine-tuned-KoreanIndoNLI-KorNLI-with-bert-kor-base \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-finetuned_bert_mrpc_ndugar_en.md b/docs/_posts/ahmedlone127/2023-10-25-finetuned_bert_mrpc_ndugar_en.md new file mode 100644 index 00000000000000..92a237b46c2e5b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-finetuned_bert_mrpc_ndugar_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English finetuned_bert_mrpc_ndugar BertForSequenceClassification from NDugar +author: John Snow Labs +name: finetuned_bert_mrpc_ndugar +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`finetuned_bert_mrpc_ndugar` is a English model originally trained by NDugar. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/finetuned_bert_mrpc_ndugar_en_5.1.4_3.4_1698226789566.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/finetuned_bert_mrpc_ndugar_en_5.1.4_3.4_1698226789566.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("finetuned_bert_mrpc_ndugar","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("finetuned_bert_mrpc_ndugar","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|finetuned_bert_mrpc_ndugar| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.9 MB| + +## References + +https://huggingface.co/NDugar/finetuned-bert-mrpc \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_12_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_12_en.md new file mode 100644 index 00000000000000..d407570ebbe125 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_12_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_12 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_12 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_12` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_12_en_5.1.4_3.4_1698216256946.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_12_en_5.1.4_3.4_1698216256946.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_12","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_12","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_12| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-12 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_14_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_14_en.md new file mode 100644 index 00000000000000..926c43f8080c6f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_14_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_14 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_14 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_14` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_14_en_5.1.4_3.4_1698216461612.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_14_en_5.1.4_3.4_1698216461612.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_14","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_14","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_14| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-14 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_18_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_18_en.md new file mode 100644 index 00000000000000..24ed3f394e1b7a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_18_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_18 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_18 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_18` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_18_en_5.1.4_3.4_1698216649878.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_18_en_5.1.4_3.4_1698216649878.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_18","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_18","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_18| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-18 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_19_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_19_en.md new file mode 100644 index 00000000000000..eff358c5fb7547 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_19_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_19 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_19 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_19` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_19_en_5.1.4_3.4_1698218217176.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_19_en_5.1.4_3.4_1698218217176.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_19","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_19","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_19| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-19 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_21_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_21_en.md new file mode 100644 index 00000000000000..f3a087bdcfa5b5 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_21_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_21 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_21 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_21` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_21_en_5.1.4_3.4_1698217595519.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_21_en_5.1.4_3.4_1698217595519.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_21","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_21","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_21| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-21 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_22_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_22_en.md new file mode 100644 index 00000000000000..b40c94252c46a3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_22_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_22 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_22 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_22` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_22_en_5.1.4_3.4_1698217792710.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_22_en_5.1.4_3.4_1698217792710.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_22","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_22","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_22| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-22 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_23_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_23_en.md new file mode 100644 index 00000000000000..10f7b5ba369f76 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_23_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_23 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_23 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_23` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_23_en_5.1.4_3.4_1698222310863.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_23_en_5.1.4_3.4_1698222310863.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_23","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_23","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_23| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-23 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_24_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_24_en.md new file mode 100644 index 00000000000000..80f0e899b951eb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_24_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_24 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_24 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_24` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_24_en_5.1.4_3.4_1698222516029.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_24_en_5.1.4_3.4_1698222516029.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_24","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_24","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_24| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-24 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_26_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_26_en.md new file mode 100644 index 00000000000000..5ad2b7a3ce6c60 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_26_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_26 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_26 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_26` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_26_en_5.1.4_3.4_1698219644965.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_26_en_5.1.4_3.4_1698219644965.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_26","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_26","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_26| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-26 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_30_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_30_en.md new file mode 100644 index 00000000000000..6ddedc444a2eea --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_30_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_30 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_30 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_30` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_30_en_5.1.4_3.4_1698219245865.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_30_en_5.1.4_3.4_1698219245865.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_30","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_30","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_30| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-30 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_31_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_31_en.md new file mode 100644 index 00000000000000..9164a916b483c0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_31_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_31 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_31 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_31` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_31_en_5.1.4_3.4_1698218399794.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_31_en_5.1.4_3.4_1698218399794.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_31","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_31","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_31| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-31 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_32_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_32_en.md new file mode 100644 index 00000000000000..64ea0587bf2874 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_32_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_32 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_32 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_32` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_32_en_5.1.4_3.4_1698219435732.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_32_en_5.1.4_3.4_1698219435732.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_32","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_32","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_32| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-32 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_33_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_33_en.md new file mode 100644 index 00000000000000..ee7679c3eca54d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_33_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_33 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_33 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_33` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_33_en_5.1.4_3.4_1698219845008.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_33_en_5.1.4_3.4_1698219845008.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_33","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_33","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_33| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-33 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_34_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_34_en.md new file mode 100644 index 00000000000000..d1e5636311de44 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_34_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_34 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_34 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_34` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_34_en_5.1.4_3.4_1698220231904.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_34_en_5.1.4_3.4_1698220231904.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_34","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_34","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_34| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-34 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_35_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_35_en.md new file mode 100644 index 00000000000000..da0bd10c0c1f63 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_35_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_35 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_35 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_35` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_35_en_5.1.4_3.4_1698220033273.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_35_en_5.1.4_3.4_1698220033273.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_35","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_35","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_35| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-35 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_36_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_36_en.md new file mode 100644 index 00000000000000..cfcef8587f4844 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_36_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_36 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_36 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_36` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_36_en_5.1.4_3.4_1698220575602.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_36_en_5.1.4_3.4_1698220575602.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_36","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_36","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_36| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-36 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_37_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_37_en.md new file mode 100644 index 00000000000000..02cdb814d6ab38 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_37_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_37 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_37 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_37` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_37_en_5.1.4_3.4_1698220419732.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_37_en_5.1.4_3.4_1698220419732.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_37","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_37","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_37| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-37 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_38_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_38_en.md new file mode 100644 index 00000000000000..b82bfd6d3288aa --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_38_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_38 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_38 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_38` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_38_en_5.1.4_3.4_1698220977338.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_38_en_5.1.4_3.4_1698220977338.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_38","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_38","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_38| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-38 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_39_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_39_en.md new file mode 100644 index 00000000000000..76d2b0e394ff87 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_39_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_39 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_39 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_39` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_39_en_5.1.4_3.4_1698221378949.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_39_en_5.1.4_3.4_1698221378949.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_39","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_39","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_39| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-39 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_3_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_3_en.md new file mode 100644 index 00000000000000..8150098741b8bf --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_3_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_3 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_3 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_3` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_3_en_5.1.4_3.4_1698215297155.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_3_en_5.1.4_3.4_1698215297155.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_3","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_3","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_3| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-3 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_40_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_40_en.md new file mode 100644 index 00000000000000..cb7ef6fdf253d1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_40_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_40 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_40 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_40` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_40_en_5.1.4_3.4_1698221167152.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_40_en_5.1.4_3.4_1698221167152.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_40","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_40","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_40| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-40 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_41_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_41_en.md new file mode 100644 index 00000000000000..98b5a18461d1ed --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_41_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_41 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_41 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_41` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_41_en_5.1.4_3.4_1698220788822.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_41_en_5.1.4_3.4_1698220788822.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_41","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_41","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_41| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-41 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_42_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_42_en.md new file mode 100644 index 00000000000000..208db8035d1ad9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_42_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_42 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_42 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_42` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_42_en_5.1.4_3.4_1698221947943.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_42_en_5.1.4_3.4_1698221947943.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_42","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_42","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_42| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-42 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_43_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_43_en.md new file mode 100644 index 00000000000000..98b58fc5562163 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_43_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_43 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_43 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_43` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_43_en_5.1.4_3.4_1698221771690.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_43_en_5.1.4_3.4_1698221771690.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_43","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_43","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_43| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-43 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_44_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_44_en.md new file mode 100644 index 00000000000000..86685d30bbac38 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_44_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_44 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_44 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_44` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_44_en_5.1.4_3.4_1698222126299.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_44_en_5.1.4_3.4_1698222126299.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_44","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_44","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_44| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-44 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_45_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_45_en.md new file mode 100644 index 00000000000000..9e80699e8a0ae9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_45_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_45 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_45 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_45` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_45_en_5.1.4_3.4_1698221572355.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_45_en_5.1.4_3.4_1698221572355.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_45","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_45","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_45| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-45 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_46_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_46_en.md new file mode 100644 index 00000000000000..4a5551ef179908 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_46_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_46 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_46 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_46` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_46_en_5.1.4_3.4_1698222695220.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_46_en_5.1.4_3.4_1698222695220.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_46","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_46","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_46| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-46 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_47_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_47_en.md new file mode 100644 index 00000000000000..abe8336f4ea9a2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_47_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_47 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_47 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_47` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_47_en_5.1.4_3.4_1698222867221.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_47_en_5.1.4_3.4_1698222867221.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_47","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_47","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_47| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-47 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_48_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_48_en.md new file mode 100644 index 00000000000000..abce1cdf1dcc68 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_48_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_48 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_48 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_48` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_48_en_5.1.4_3.4_1698225719514.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_48_en_5.1.4_3.4_1698225719514.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_48","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_48","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_48| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-48 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_49_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_49_en.md new file mode 100644 index 00000000000000..9f0c57140f6d0d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_49_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_49 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_49 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_49` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_49_en_5.1.4_3.4_1698229026818.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_49_en_5.1.4_3.4_1698229026818.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_49","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_49","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_49| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-49 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_50_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_50_en.md new file mode 100644 index 00000000000000..cd94e000f51da6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_50_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_50 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_50 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_50` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_50_en_5.1.4_3.4_1698231600698.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_50_en_5.1.4_3.4_1698231600698.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_50","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_50","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_50| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-50 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_51_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_51_en.md new file mode 100644 index 00000000000000..18bc0c70d31135 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_51_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_51 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_51 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_51` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_51_en_5.1.4_3.4_1698227400253.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_51_en_5.1.4_3.4_1698227400253.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_51","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_51","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_51| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-51 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_52_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_52_en.md new file mode 100644 index 00000000000000..0213934506a26a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_52_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_52 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_52 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_52` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_52_en_5.1.4_3.4_1698224786799.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_52_en_5.1.4_3.4_1698224786799.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_52","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_52","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_52| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-52 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_53_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_53_en.md new file mode 100644 index 00000000000000..71f33047ff8ca0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_53_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_53 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_53 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_53` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_53_en_5.1.4_3.4_1698225000509.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_53_en_5.1.4_3.4_1698225000509.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_53","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_53","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_53| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-53 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_54_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_54_en.md new file mode 100644 index 00000000000000..2390033ee09458 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_54_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_54 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_54 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_54` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_54_en_5.1.4_3.4_1698230803166.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_54_en_5.1.4_3.4_1698230803166.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_54","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_54","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_54| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-54 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_55_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_55_en.md new file mode 100644 index 00000000000000..d273e6a62e91d0 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_55_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_55 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_55 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_55` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_55_en_5.1.4_3.4_1698229934190.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_55_en_5.1.4_3.4_1698229934190.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_55","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_55","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_55| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-55 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_56_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_56_en.md new file mode 100644 index 00000000000000..3cca9930f87549 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_56_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_56 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_56 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_56` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_56_en_5.1.4_3.4_1698226620229.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_56_en_5.1.4_3.4_1698226620229.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_56","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_56","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_56| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-56 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_57_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_57_en.md new file mode 100644 index 00000000000000..6333ebd3b81807 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_57_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_57 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_57 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_57` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_57_en_5.1.4_3.4_1698228126156.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_57_en_5.1.4_3.4_1698228126156.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_57","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_57","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_57| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-57 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_58_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_58_en.md new file mode 100644 index 00000000000000..d6d1a9450b8f47 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_58_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_58 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_58 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_58` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_58_en_5.1.4_3.4_1698235996382.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_58_en_5.1.4_3.4_1698235996382.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_58","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_58","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_58| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-58 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_59_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_59_en.md new file mode 100644 index 00000000000000..0fa6ae8ccc1213 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_59_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_59 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_59 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_59` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_59_en_5.1.4_3.4_1698236948806.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_59_en_5.1.4_3.4_1698236948806.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_59","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_59","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_59| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-59 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_60_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_60_en.md new file mode 100644 index 00000000000000..8cbdb3d1be1f56 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_60_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_60 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_60 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_60` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_60_en_5.1.4_3.4_1698224363748.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_60_en_5.1.4_3.4_1698224363748.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_60","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_60","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_60| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-60 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_61_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_61_en.md new file mode 100644 index 00000000000000..1b7d5299d6c7dd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_61_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_61 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_61 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_61` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_61_en_5.1.4_3.4_1698237883855.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_61_en_5.1.4_3.4_1698237883855.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_61","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_61","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_61| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-61 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_62_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_62_en.md new file mode 100644 index 00000000000000..6e1ab25b09c2e1 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_62_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_62 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_62 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_62` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_62_en_5.1.4_3.4_1698239026933.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_62_en_5.1.4_3.4_1698239026933.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_62","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_62","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_62| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-62 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_63_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_63_en.md new file mode 100644 index 00000000000000..37e917d2144fad --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_63_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_63 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_63 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_63` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_63_en_5.1.4_3.4_1698224150303.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_63_en_5.1.4_3.4_1698224150303.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_63","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_63","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_63| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-63 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_64_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_64_en.md new file mode 100644 index 00000000000000..fc8b6cad2d4af7 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_64_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_64 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_64 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_64` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_64_en_5.1.4_3.4_1698232386985.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_64_en_5.1.4_3.4_1698232386985.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_64","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_64","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_64| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-64 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_65_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_65_en.md new file mode 100644 index 00000000000000..3c511abdf76e74 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_65_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_65 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_65 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_65` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_65_en_5.1.4_3.4_1698234886083.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_65_en_5.1.4_3.4_1698234886083.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_65","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_65","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_65| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-65 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_66_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_66_en.md new file mode 100644 index 00000000000000..58193b59a8aa0d --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_66_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_66 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_66 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_66` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_66_en_5.1.4_3.4_1698239876018.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_66_en_5.1.4_3.4_1698239876018.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_66","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_66","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_66| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-66 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_67_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_67_en.md new file mode 100644 index 00000000000000..fa12338d9dd42a --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_67_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_67 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_67 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_67` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_67_en_5.1.4_3.4_1698233984646.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_67_en_5.1.4_3.4_1698233984646.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_67","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_67","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_67| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-67 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_68_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_68_en.md new file mode 100644 index 00000000000000..a6dddfecc8d91c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_68_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_68 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_68 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_68` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_68_en_5.1.4_3.4_1698223587499.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_68_en_5.1.4_3.4_1698223587499.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_68","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_68","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_68| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-68 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_69_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_69_en.md new file mode 100644 index 00000000000000..124ef297147464 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_69_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_69 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_69 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_69` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_69_en_5.1.4_3.4_1698224583571.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_69_en_5.1.4_3.4_1698224583571.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_69","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_69","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_69| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-69 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_70_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_70_en.md new file mode 100644 index 00000000000000..b609c5b69696b2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_70_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_70 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_70 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_70` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_70_en_5.1.4_3.4_1698233231183.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_70_en_5.1.4_3.4_1698233231183.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_70","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_70","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_70| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-70 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_71_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_71_en.md new file mode 100644 index 00000000000000..9a6ee5a84ab843 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_71_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_71 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_71 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_71` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_71_en_5.1.4_3.4_1698223045460.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_71_en_5.1.4_3.4_1698223045460.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_71","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_71","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_71| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-71 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_72_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_72_en.md new file mode 100644 index 00000000000000..8e8a4e73a26404 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_72_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_72 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_72 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_72` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_72_en_5.1.4_3.4_1698223744727.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_72_en_5.1.4_3.4_1698223744727.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_72","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_72","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_72| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-72 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_73_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_73_en.md new file mode 100644 index 00000000000000..d3a2d9ac149662 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_73_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_73 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_73 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_73` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_73_en_5.1.4_3.4_1698223219896.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_73_en_5.1.4_3.4_1698223219896.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_73","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_73","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_73| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-73 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_74_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_74_en.md new file mode 100644 index 00000000000000..2d4bc553a6b360 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_74_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_74 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_74 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_74` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_74_en_5.1.4_3.4_1698223397781.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_74_en_5.1.4_3.4_1698223397781.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_74","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_74","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_74| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-74 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_75_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_75_en.md new file mode 100644 index 00000000000000..c6b7e2cf9c1edd --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_75_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_75 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_75 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_75` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_75_en_5.1.4_3.4_1698223965234.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_75_en_5.1.4_3.4_1698223965234.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_75","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_75","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_75| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-75 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_76_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_76_en.md new file mode 100644 index 00000000000000..0084c059fa22af --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_76_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_76 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_76 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_76` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_76_en_5.1.4_3.4_1698240706542.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_76_en_5.1.4_3.4_1698240706542.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_76","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_76","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_76| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-76 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_77_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_77_en.md new file mode 100644 index 00000000000000..24e5ce5121f174 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_77_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_77 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_77 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_77` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_77_en_5.1.4_3.4_1698241641782.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_77_en_5.1.4_3.4_1698241641782.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_77","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_77","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_77| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-77 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_81_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_81_en.md new file mode 100644 index 00000000000000..11f590ad3c0e39 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_81_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_81 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_81 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_81` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_81_en_5.1.4_3.4_1698242418276.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_81_en_5.1.4_3.4_1698242418276.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_81","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_81","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_81| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-81 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_82_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_82_en.md new file mode 100644 index 00000000000000..c90ed243a1122c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_82_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_82 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_82 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_82` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_82_en_5.1.4_3.4_1698245210556.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_82_en_5.1.4_3.4_1698245210556.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_82","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_82","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_82| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-82 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_89_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_89_en.md new file mode 100644 index 00000000000000..104864c31bf932 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_89_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_89 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_89 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_89` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_89_en_5.1.4_3.4_1698244522753.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_89_en_5.1.4_3.4_1698244522753.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_89","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_89","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_89| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-89 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_91_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_91_en.md new file mode 100644 index 00000000000000..f9779e0c363f8b --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_91_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_91 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_91 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_91` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_91_en_5.1.4_3.4_1698243759493.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_91_en_5.1.4_3.4_1698243759493.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_91","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_91","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_91| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-91 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_9_en.md b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_9_en.md new file mode 100644 index 00000000000000..f63cd5d3f30d5c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-goog_bert_ft_cola_9_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English goog_bert_ft_cola_9 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: goog_bert_ft_cola_9 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`goog_bert_ft_cola_9` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_9_en_5.1.4_3.4_1698215840044.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/goog_bert_ft_cola_9_en_5.1.4_3.4_1698215840044.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_9","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("goog_bert_ft_cola_9","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|goog_bert_ft_cola_9| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/goog_bert_ft_cola-9 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-hindi_const21_hibert_final_en.md b/docs/_posts/ahmedlone127/2023-10-25-hindi_const21_hibert_final_en.md new file mode 100644 index 00000000000000..67a0c24f3195c4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-hindi_const21_hibert_final_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English hindi_const21_hibert_final BertForSequenceClassification from Maha +author: John Snow Labs +name: hindi_const21_hibert_final +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`hindi_const21_hibert_final` is a English model originally trained by Maha. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/hindi_const21_hibert_final_en_5.1.4_3.4_1698224332652.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/hindi_const21_hibert_final_en_5.1.4_3.4_1698224332652.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("hindi_const21_hibert_final","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("hindi_const21_hibert_final","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|hindi_const21_hibert_final| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|611.4 MB| + +## References + +https://huggingface.co/Maha/hi-const21-hibert_final \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-incivility_v2_final_tulio_chilean_spanish_bert_en.md b/docs/_posts/ahmedlone127/2023-10-25-incivility_v2_final_tulio_chilean_spanish_bert_en.md new file mode 100644 index 00000000000000..b2d9d776af8270 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-incivility_v2_final_tulio_chilean_spanish_bert_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English incivility_v2_final_tulio_chilean_spanish_bert BertForSequenceClassification from jorgeortizfuentes +author: John Snow Labs +name: incivility_v2_final_tulio_chilean_spanish_bert +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`incivility_v2_final_tulio_chilean_spanish_bert` is a English model originally trained by jorgeortizfuentes. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/incivility_v2_final_tulio_chilean_spanish_bert_en_5.1.4_3.4_1698209746645.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/incivility_v2_final_tulio_chilean_spanish_bert_en_5.1.4_3.4_1698209746645.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("incivility_v2_final_tulio_chilean_spanish_bert","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("incivility_v2_final_tulio_chilean_spanish_bert","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|incivility_v2_final_tulio_chilean_spanish_bert| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|411.5 MB| + +## References + +https://huggingface.co/jorgeortizfuentes/incivility_v2_final-tulio-chilean-spanish-bert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-indobertnewstest_rizalmilyardi_en.md b/docs/_posts/ahmedlone127/2023-10-25-indobertnewstest_rizalmilyardi_en.md new file mode 100644 index 00000000000000..461c447d6d40dc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-indobertnewstest_rizalmilyardi_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English indobertnewstest_rizalmilyardi BertForSequenceClassification from rizalmilyardi +author: John Snow Labs +name: indobertnewstest_rizalmilyardi +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`indobertnewstest_rizalmilyardi` is a English model originally trained by rizalmilyardi. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/indobertnewstest_rizalmilyardi_en_5.1.4_3.4_1698211956208.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/indobertnewstest_rizalmilyardi_en_5.1.4_3.4_1698211956208.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("indobertnewstest_rizalmilyardi","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("indobertnewstest_rizalmilyardi","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|indobertnewstest_rizalmilyardi| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|414.0 MB| + +## References + +https://huggingface.co/rizalmilyardi/IndobertNewsTest \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-legal_bert_tpb_clause_class_en.md b/docs/_posts/ahmedlone127/2023-10-25-legal_bert_tpb_clause_class_en.md new file mode 100644 index 00000000000000..db9dffa14be5d4 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-legal_bert_tpb_clause_class_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English legal_bert_tpb_clause_class BertForSequenceClassification from frankkuete +author: John Snow Labs +name: legal_bert_tpb_clause_class +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`legal_bert_tpb_clause_class` is a English model originally trained by frankkuete. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/legal_bert_tpb_clause_class_en_5.1.4_3.4_1698237815681.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/legal_bert_tpb_clause_class_en_5.1.4_3.4_1698237815681.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("legal_bert_tpb_clause_class","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("legal_bert_tpb_clause_class","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|legal_bert_tpb_clause_class| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.5 MB| + +## References + +https://huggingface.co/frankkuete/legal-bert-tpb-clause-class \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_ssec_en.md b/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_ssec_en.md new file mode 100644 index 00000000000000..9ad40abc891aba --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_ssec_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English mengzi_bert_base_fin_ssec BertForSequenceClassification from hw2942 +author: John Snow Labs +name: mengzi_bert_base_fin_ssec +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mengzi_bert_base_fin_ssec` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mengzi_bert_base_fin_ssec_en_5.1.4_3.4_1698222925679.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mengzi_bert_base_fin_ssec_en_5.1.4_3.4_1698222925679.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("mengzi_bert_base_fin_ssec","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("mengzi_bert_base_fin_ssec","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mengzi_bert_base_fin_ssec| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.1 MB| + +## References + +https://huggingface.co/hw2942/mengzi-bert-base-fin-SSEC \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en.md b/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en.md new file mode 100644 index 00000000000000..7609c326cdf263 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en_5.1.4_3.4_1698219379071.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1_en_5.1.4_3.4_1698219379071.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v1| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.1 MB| + +## References + +https://huggingface.co/hw2942/mengzi-bert-base-fin-wallstreetcn-morning-news-market-overview-open-SSEC-f1-v1 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22_en.md b/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22_en.md new file mode 100644 index 00000000000000..3cff0c16472972 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22_en_5.1.4_3.4_1698223114906.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22_en_5.1.4_3.4_1698223114906.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_f1_v22| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.1 MB| + +## References + +https://huggingface.co/hw2942/mengzi-bert-base-fin-wallstreetcn-morning-news-market-overview-open-SSEC-f1-v22 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2_en.md b/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2_en.md new file mode 100644 index 00000000000000..db46416dce0017 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2 BertForSequenceClassification from hw2942 +author: John Snow Labs +name: mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2` is a English model originally trained by hw2942. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2_en_5.1.4_3.4_1698220731080.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2_en_5.1.4_3.4_1698220731080.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mengzi_bert_base_fin_wallstreetcn_morning_news_market_overview_open_ssec_v2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|383.1 MB| + +## References + +https://huggingface.co/hw2942/mengzi-bert-base-fin-wallstreetcn-morning-news-market-overview-open-SSEC-v2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-mini_bert_distilled_en.md b/docs/_posts/ahmedlone127/2023-10-25-mini_bert_distilled_en.md new file mode 100644 index 00000000000000..19b3cb261a694c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-mini_bert_distilled_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English mini_bert_distilled BertForSequenceClassification from moshew +author: John Snow Labs +name: mini_bert_distilled +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mini_bert_distilled` is a English model originally trained by moshew. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/mini_bert_distilled_en_5.1.4_3.4_1698240255617.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mini_bert_distilled_en_5.1.4_3.4_1698240255617.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("mini_bert_distilled","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("mini_bert_distilled","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|mini_bert_distilled| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|42.2 MB| + +## References + +https://huggingface.co/moshew/Mini-bert-distilled \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_2_en.md b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_2_en.md new file mode 100644 index 00000000000000..0485e80e906c86 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_2_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English norbert2_sentiment_norec_2 BertForSequenceClassification from NTCAL +author: John Snow Labs +name: norbert2_sentiment_norec_2 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`norbert2_sentiment_norec_2` is a English model originally trained by NTCAL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_2_en_5.1.4_3.4_1698233003739.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_2_en_5.1.4_3.4_1698233003739.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_2","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_2","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|norbert2_sentiment_norec_2| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/NTCAL/norbert2_sentiment_norec_2 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_4_en.md b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_4_en.md new file mode 100644 index 00000000000000..f7cec3abb9b5ee --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_4_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English norbert2_sentiment_norec_4 BertForSequenceClassification from NTCAL +author: John Snow Labs +name: norbert2_sentiment_norec_4 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`norbert2_sentiment_norec_4` is a English model originally trained by NTCAL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_4_en_5.1.4_3.4_1698235996431.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_4_en_5.1.4_3.4_1698235996431.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_4","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_4","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|norbert2_sentiment_norec_4| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/NTCAL/norbert2_sentiment_norec_4 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_6_en.md b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_6_en.md new file mode 100644 index 00000000000000..60212355c661b3 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_6_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English norbert2_sentiment_norec_6 BertForSequenceClassification from NTCAL +author: John Snow Labs +name: norbert2_sentiment_norec_6 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`norbert2_sentiment_norec_6` is a English model originally trained by NTCAL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_6_en_5.1.4_3.4_1698237683293.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_6_en_5.1.4_3.4_1698237683293.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_6","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_6","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|norbert2_sentiment_norec_6| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/NTCAL/norbert2_sentiment_norec_6 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_7_en.md b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_7_en.md new file mode 100644 index 00000000000000..1927f729a20ea6 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_7_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English norbert2_sentiment_norec_7 BertForSequenceClassification from NTCAL +author: John Snow Labs +name: norbert2_sentiment_norec_7 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`norbert2_sentiment_norec_7` is a English model originally trained by NTCAL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_7_en_5.1.4_3.4_1698239342573.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_7_en_5.1.4_3.4_1698239342573.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_7","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_7","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|norbert2_sentiment_norec_7| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/NTCAL/norbert2_sentiment_norec_7 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_8_en.md b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_8_en.md new file mode 100644 index 00000000000000..fe27aa1b1fce53 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_8_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English norbert2_sentiment_norec_8 BertForSequenceClassification from NTCAL +author: John Snow Labs +name: norbert2_sentiment_norec_8 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`norbert2_sentiment_norec_8` is a English model originally trained by NTCAL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_8_en_5.1.4_3.4_1698244059994.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_8_en_5.1.4_3.4_1698244059994.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_8","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_8","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|norbert2_sentiment_norec_8| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/NTCAL/norbert2_sentiment_norec_8 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_9_en.md b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_9_en.md new file mode 100644 index 00000000000000..13708009c12d63 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-norbert2_sentiment_norec_9_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English norbert2_sentiment_norec_9 BertForSequenceClassification from NTCAL +author: John Snow Labs +name: norbert2_sentiment_norec_9 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`norbert2_sentiment_norec_9` is a English model originally trained by NTCAL. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_9_en_5.1.4_3.4_1698245023007.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/norbert2_sentiment_norec_9_en_5.1.4_3.4_1698245023007.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_9","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("norbert2_sentiment_norec_9","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|norbert2_sentiment_norec_9| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|467.4 MB| + +## References + +https://huggingface.co/NTCAL/norbert2_sentiment_norec_9 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-norsk_bert_fintuned_en.md b/docs/_posts/ahmedlone127/2023-10-25-norsk_bert_fintuned_en.md new file mode 100644 index 00000000000000..840c67aedb048e --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-norsk_bert_fintuned_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English norsk_bert_fintuned BertForSequenceClassification from kirisums +author: John Snow Labs +name: norsk_bert_fintuned +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`norsk_bert_fintuned` is a English model originally trained by kirisums. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/norsk_bert_fintuned_en_5.1.4_3.4_1698224676169.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/norsk_bert_fintuned_en_5.1.4_3.4_1698224676169.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("norsk_bert_fintuned","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("norsk_bert_fintuned","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|norsk_bert_fintuned| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|668.4 MB| + +## References + +https://huggingface.co/kirisums/norsk-bert-fintuned \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-ogbv_gender_bert_hindi_english_hasoc20a_fin_en.md b/docs/_posts/ahmedlone127/2023-10-25-ogbv_gender_bert_hindi_english_hasoc20a_fin_en.md new file mode 100644 index 00000000000000..0cadc0726cfaa2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-ogbv_gender_bert_hindi_english_hasoc20a_fin_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English ogbv_gender_bert_hindi_english_hasoc20a_fin BertForSequenceClassification from Maha +author: John Snow Labs +name: ogbv_gender_bert_hindi_english_hasoc20a_fin +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`ogbv_gender_bert_hindi_english_hasoc20a_fin` is a English model originally trained by Maha. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/ogbv_gender_bert_hindi_english_hasoc20a_fin_en_5.1.4_3.4_1698224066734.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/ogbv_gender_bert_hindi_english_hasoc20a_fin_en_5.1.4_3.4_1698224066734.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("ogbv_gender_bert_hindi_english_hasoc20a_fin","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("ogbv_gender_bert_hindi_english_hasoc20a_fin","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|ogbv_gender_bert_hindi_english_hasoc20a_fin| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|667.3 MB| + +## References + +https://huggingface.co/Maha/OGBV-gender-bert-hi-en-hasoc20a-fin \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-pipp_finder_bert_base_cased_en.md b/docs/_posts/ahmedlone127/2023-10-25-pipp_finder_bert_base_cased_en.md new file mode 100644 index 00000000000000..2ce48d13b73d85 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-pipp_finder_bert_base_cased_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English pipp_finder_bert_base_cased BertForSequenceClassification from cgpotts +author: John Snow Labs +name: pipp_finder_bert_base_cased +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`pipp_finder_bert_base_cased` is a English model originally trained by cgpotts. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/pipp_finder_bert_base_cased_en_5.1.4_3.4_1698220093324.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/pipp_finder_bert_base_cased_en_5.1.4_3.4_1698220093324.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("pipp_finder_bert_base_cased","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("pipp_finder_bert_base_cased","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|pipp_finder_bert_base_cased| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.9 MB| + +## References + +https://huggingface.co/cgpotts/pipp-finder-bert-base-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-roberta_fake_real_en.md b/docs/_posts/ahmedlone127/2023-10-25-roberta_fake_real_en.md new file mode 100644 index 00000000000000..ff3001149544cc --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-roberta_fake_real_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English roberta_fake_real BertForSequenceClassification from PravallikaMyneni +author: John Snow Labs +name: roberta_fake_real +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`roberta_fake_real` is a English model originally trained by PravallikaMyneni. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/roberta_fake_real_en_5.1.4_3.4_1698221775747.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/roberta_fake_real_en_5.1.4_3.4_1698221775747.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("roberta_fake_real","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("roberta_fake_real","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|roberta_fake_real| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|405.9 MB| + +## References + +https://huggingface.co/PravallikaMyneni/roberta_fake_real \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-rubert_large_emotion_russian_cedr_m7_en.md b/docs/_posts/ahmedlone127/2023-10-25-rubert_large_emotion_russian_cedr_m7_en.md new file mode 100644 index 00000000000000..f9b4f7acf93a44 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-rubert_large_emotion_russian_cedr_m7_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English rubert_large_emotion_russian_cedr_m7 BertForSequenceClassification from Aniemore +author: John Snow Labs +name: rubert_large_emotion_russian_cedr_m7 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`rubert_large_emotion_russian_cedr_m7` is a English model originally trained by Aniemore. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/rubert_large_emotion_russian_cedr_m7_en_5.1.4_3.4_1698208388605.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/rubert_large_emotion_russian_cedr_m7_en_5.1.4_3.4_1698208388605.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("rubert_large_emotion_russian_cedr_m7","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("rubert_large_emotion_russian_cedr_m7","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|rubert_large_emotion_russian_cedr_m7| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.6 GB| + +## References + +https://huggingface.co/Aniemore/rubert-large-emotion-russian-cedr-m7 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-rubert_rusentitweet_sismetanin_en.md b/docs/_posts/ahmedlone127/2023-10-25-rubert_rusentitweet_sismetanin_en.md new file mode 100644 index 00000000000000..e9f32b9b16863f --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-rubert_rusentitweet_sismetanin_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English rubert_rusentitweet_sismetanin BertForSequenceClassification from sismetanin +author: John Snow Labs +name: rubert_rusentitweet_sismetanin +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`rubert_rusentitweet_sismetanin` is a English model originally trained by sismetanin. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/rubert_rusentitweet_sismetanin_en_5.1.4_3.4_1698243502522.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/rubert_rusentitweet_sismetanin_en_5.1.4_3.4_1698243502522.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("rubert_rusentitweet_sismetanin","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("rubert_rusentitweet_sismetanin","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|rubert_rusentitweet_sismetanin| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|666.5 MB| + +## References + +https://huggingface.co/sismetanin/rubert-rusentitweet \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-samyarn_bert_base_multilingual_cased_xx.md b/docs/_posts/ahmedlone127/2023-10-25-samyarn_bert_base_multilingual_cased_xx.md new file mode 100644 index 00000000000000..ea42b4ff0221b2 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-samyarn_bert_base_multilingual_cased_xx.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Multilingual samyarn_bert_base_multilingual_cased BertForSequenceClassification from Kao +author: John Snow Labs +name: samyarn_bert_base_multilingual_cased +date: 2023-10-25 +tags: [bert, xx, open_source, sequence_classification, onnx] +task: Text Classification +language: xx +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`samyarn_bert_base_multilingual_cased` is a Multilingual model originally trained by Kao. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/samyarn_bert_base_multilingual_cased_xx_5.1.4_3.4_1698220388695.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/samyarn_bert_base_multilingual_cased_xx_5.1.4_3.4_1698220388695.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("samyarn_bert_base_multilingual_cased","xx")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("samyarn_bert_base_multilingual_cased","xx") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|samyarn_bert_base_multilingual_cased| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|xx| +|Size:|667.3 MB| + +## References + +https://huggingface.co/Kao/samyarn-bert-base-multilingual-cased \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-sentiment_hts2_hubert_hungarian_hu.md b/docs/_posts/ahmedlone127/2023-10-25-sentiment_hts2_hubert_hungarian_hu.md new file mode 100644 index 00000000000000..76fb842f567620 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-sentiment_hts2_hubert_hungarian_hu.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Hungarian sentiment_hts2_hubert_hungarian BertForSequenceClassification from NYTK +author: John Snow Labs +name: sentiment_hts2_hubert_hungarian +date: 2023-10-25 +tags: [bert, hu, open_source, sequence_classification, onnx] +task: Text Classification +language: hu +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`sentiment_hts2_hubert_hungarian` is a Hungarian model originally trained by NYTK. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/sentiment_hts2_hubert_hungarian_hu_5.1.4_3.4_1698227753323.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/sentiment_hts2_hubert_hungarian_hu_5.1.4_3.4_1698227753323.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("sentiment_hts2_hubert_hungarian","hu")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("sentiment_hts2_hubert_hungarian","hu") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|sentiment_hts2_hubert_hungarian| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|hu| +|Size:|414.7 MB| + +## References + +https://huggingface.co/NYTK/sentiment-hts2-hubert-hungarian \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-sentiment_hts5_hubert_hungarian_hu.md b/docs/_posts/ahmedlone127/2023-10-25-sentiment_hts5_hubert_hungarian_hu.md new file mode 100644 index 00000000000000..025fc5dbefc631 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-sentiment_hts5_hubert_hungarian_hu.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Hungarian sentiment_hts5_hubert_hungarian BertForSequenceClassification from NYTK +author: John Snow Labs +name: sentiment_hts5_hubert_hungarian +date: 2023-10-25 +tags: [bert, hu, open_source, sequence_classification, onnx] +task: Text Classification +language: hu +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`sentiment_hts5_hubert_hungarian` is a Hungarian model originally trained by NYTK. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/sentiment_hts5_hubert_hungarian_hu_5.1.4_3.4_1698228545238.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/sentiment_hts5_hubert_hungarian_hu_5.1.4_3.4_1698228545238.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("sentiment_hts5_hubert_hungarian","hu")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("sentiment_hts5_hubert_hungarian","hu") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|sentiment_hts5_hubert_hungarian| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|hu| +|Size:|414.7 MB| + +## References + +https://huggingface.co/NYTK/sentiment-hts5-hubert-hungarian \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-solved_finbert_tone_en.md b/docs/_posts/ahmedlone127/2023-10-25-solved_finbert_tone_en.md new file mode 100644 index 00000000000000..7c6d502cfcf9f8 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-solved_finbert_tone_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English solved_finbert_tone BertForSequenceClassification from ldeb +author: John Snow Labs +name: solved_finbert_tone +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`solved_finbert_tone` is a English model originally trained by ldeb. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/solved_finbert_tone_en_5.1.4_3.4_1698211497295.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/solved_finbert_tone_en_5.1.4_3.4_1698211497295.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("solved_finbert_tone","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("solved_finbert_tone","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|solved_finbert_tone| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|411.6 MB| + +## References + +https://huggingface.co/ldeb/solved-finbert-tone \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-std_0pnt2_bert_ft_cola_16_en.md b/docs/_posts/ahmedlone127/2023-10-25-std_0pnt2_bert_ft_cola_16_en.md new file mode 100644 index 00000000000000..c0542f65b189d9 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-std_0pnt2_bert_ft_cola_16_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English std_0pnt2_bert_ft_cola_16 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: std_0pnt2_bert_ft_cola_16 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`std_0pnt2_bert_ft_cola_16` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/std_0pnt2_bert_ft_cola_16_en_5.1.4_3.4_1698202138259.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/std_0pnt2_bert_ft_cola_16_en_5.1.4_3.4_1698202138259.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("std_0pnt2_bert_ft_cola_16","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("std_0pnt2_bert_ft_cola_16","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|std_0pnt2_bert_ft_cola_16| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/std_0pnt2_bert_ft_cola-16 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-std_0pnt2_bert_ft_cola_62_en.md b/docs/_posts/ahmedlone127/2023-10-25-std_0pnt2_bert_ft_cola_62_en.md new file mode 100644 index 00000000000000..2f78fd9098a28c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-std_0pnt2_bert_ft_cola_62_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English std_0pnt2_bert_ft_cola_62 BertForSequenceClassification from Jeevesh8 +author: John Snow Labs +name: std_0pnt2_bert_ft_cola_62 +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`std_0pnt2_bert_ft_cola_62` is a English model originally trained by Jeevesh8. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/std_0pnt2_bert_ft_cola_62_en_5.1.4_3.4_1698204456665.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/std_0pnt2_bert_ft_cola_62_en_5.1.4_3.4_1698204456665.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("std_0pnt2_bert_ft_cola_62","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("std_0pnt2_bert_ft_cola_62","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|std_0pnt2_bert_ft_cola_62| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|409.4 MB| + +## References + +https://huggingface.co/Jeevesh8/std_0pnt2_bert_ft_cola-62 \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-tiny_bert_mrpc_distilled_en.md b/docs/_posts/ahmedlone127/2023-10-25-tiny_bert_mrpc_distilled_en.md new file mode 100644 index 00000000000000..80a136cb63b766 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-tiny_bert_mrpc_distilled_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English tiny_bert_mrpc_distilled BertForSequenceClassification from Sayan01 +author: John Snow Labs +name: tiny_bert_mrpc_distilled +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`tiny_bert_mrpc_distilled` is a English model originally trained by Sayan01. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/tiny_bert_mrpc_distilled_en_5.1.4_3.4_1698209972204.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/tiny_bert_mrpc_distilled_en_5.1.4_3.4_1698209972204.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("tiny_bert_mrpc_distilled","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("tiny_bert_mrpc_distilled","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|tiny_bert_mrpc_distilled| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|54.2 MB| + +## References + +https://huggingface.co/Sayan01/tiny-bert-mrpc-distilled \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-tiny_bert_sst2_distilled_kushaljoseph_en.md b/docs/_posts/ahmedlone127/2023-10-25-tiny_bert_sst2_distilled_kushaljoseph_en.md new file mode 100644 index 00000000000000..720694324591fb --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-tiny_bert_sst2_distilled_kushaljoseph_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English tiny_bert_sst2_distilled_kushaljoseph BertForSequenceClassification from kushaljoseph +author: John Snow Labs +name: tiny_bert_sst2_distilled_kushaljoseph +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`tiny_bert_sst2_distilled_kushaljoseph` is a English model originally trained by kushaljoseph. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/tiny_bert_sst2_distilled_kushaljoseph_en_5.1.4_3.4_1698234651704.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/tiny_bert_sst2_distilled_kushaljoseph_en_5.1.4_3.4_1698234651704.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("tiny_bert_sst2_distilled_kushaljoseph","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("tiny_bert_sst2_distilled_kushaljoseph","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|tiny_bert_sst2_distilled_kushaljoseph| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|16.7 MB| + +## References + +https://huggingface.co/kushaljoseph/tiny-bert-sst2-distilled \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-tonely_bert_en.md b/docs/_posts/ahmedlone127/2023-10-25-tonely_bert_en.md new file mode 100644 index 00000000000000..d28bb22dad1362 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-tonely_bert_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English tonely_bert BertForSequenceClassification from francheska-vicente +author: John Snow Labs +name: tonely_bert +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`tonely_bert` is a English model originally trained by francheska-vicente. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/tonely_bert_en_5.1.4_3.4_1698223349625.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/tonely_bert_en_5.1.4_3.4_1698223349625.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("tonely_bert","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("tonely_bert","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|tonely_bert| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|406.0 MB| + +## References + +https://huggingface.co/francheska-vicente/tonely-bert \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-twitter_disaster_bert_large_en.md b/docs/_posts/ahmedlone127/2023-10-25-twitter_disaster_bert_large_en.md new file mode 100644 index 00000000000000..54e97698c2eb2c --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-twitter_disaster_bert_large_en.md @@ -0,0 +1,97 @@ +--- +layout: model +title: English twitter_disaster_bert_large BertForSequenceClassification from ReynaQuita +author: John Snow Labs +name: twitter_disaster_bert_large +date: 2023-10-25 +tags: [bert, en, open_source, sequence_classification, onnx] +task: Text Classification +language: en +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`twitter_disaster_bert_large` is a English model originally trained by ReynaQuita. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/twitter_disaster_bert_large_en_5.1.4_3.4_1698238716080.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/twitter_disaster_bert_large_en_5.1.4_3.4_1698238716080.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("twitter_disaster_bert_large","en")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("twitter_disaster_bert_large","en") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|twitter_disaster_bert_large| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|en| +|Size:|1.3 GB| + +## References + +https://huggingface.co/ReynaQuita/twitter_disaster_bert_large \ No newline at end of file diff --git a/docs/_posts/ahmedlone127/2023-10-25-vashkontrol_sentiment_rubert_ru.md b/docs/_posts/ahmedlone127/2023-10-25-vashkontrol_sentiment_rubert_ru.md new file mode 100644 index 00000000000000..2c70fdca761862 --- /dev/null +++ b/docs/_posts/ahmedlone127/2023-10-25-vashkontrol_sentiment_rubert_ru.md @@ -0,0 +1,97 @@ +--- +layout: model +title: Russian vashkontrol_sentiment_rubert BertForSequenceClassification from kartashoffv +author: John Snow Labs +name: vashkontrol_sentiment_rubert +date: 2023-10-25 +tags: [bert, ru, open_source, sequence_classification, onnx] +task: Text Classification +language: ru +edition: Spark NLP 5.1.4 +spark_version: 3.4 +supported: true +engine: onnx +annotator: BertForSequenceClassification +article_header: + type: cover +use_language_switcher: "Python-Scala-Java" +--- + +## Description + +Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`vashkontrol_sentiment_rubert` is a Russian model originally trained by kartashoffv. + +{:.btn-box} + + +[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/vashkontrol_sentiment_rubert_ru_5.1.4_3.4_1698206312526.zip){:.button.button-orange.button-orange-trans.arr.button-icon} +[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/vashkontrol_sentiment_rubert_ru_5.1.4_3.4_1698206312526.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3} + +## How to use + + + +
+{% include programmingLanguageSelectScalaPythonNLU.html %} +```python + +document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + +tokenizer = Tokenizer()\ + .setInputCols("document")\ + .setOutputCol("token") + +sequenceClassifier = BertForSequenceClassification.pretrained("vashkontrol_sentiment_rubert","ru")\ + .setInputCols(["document","token"])\ + .setOutputCol("class") + +pipeline = Pipeline().setStages([document_assembler, tokenizer, sequenceClassifier]) + +data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text") + +result = pipeline.fit(data).transform(data) + +``` +```scala + +val document_assembler = new DocumentAssembler() + .setInputCol("text") + .setOutputCol("document") + +val tokenizer = new Tokenizer() + .setInputCols("document") + .setOutputCol("token") + +val sequenceClassifier = BertForSequenceClassification.pretrained("vashkontrol_sentiment_rubert","ru") + .setInputCols(Array("document","token")) + .setOutputCol("class") + +val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier)) + +val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text") + +val result = pipeline.fit(data).transform(data) + + +``` +
+ +{:.model-param} +## Model Information + +{:.table-model} +|---|---| +|Model Name:|vashkontrol_sentiment_rubert| +|Compatibility:|Spark NLP 5.1.4+| +|License:|Open Source| +|Edition:|Official| +|Input Labels:|[documents, token]| +|Output Labels:|[class]| +|Language:|ru| +|Size:|666.5 MB| + +## References + +https://huggingface.co/kartashoffv/vashkontrol-sentiment-rubert \ No newline at end of file