Models hub

docs/_posts/SaiDeepaPeri/2024-05-06-deepa_xlmroberta_ner_large_en_panx_en.md

@@ -0,0 +1,76 @@
+---
+layout: model
+title: Deepa Panx Model for English
+author: SaiDeepaPeri
+name: deepa_xlmroberta_ner_large_en_panx
+date: 2024-05-06
+tags: [en, open_source]
+task: Named Entity Recognition
+language: en
+edition: Spark NLP 4.1.0
+spark_version: 3.0
+supported: false
+annotator: XlmRoBertaForTokenClassification
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Named Entity Recognition trained on English panx
+
+## Predicted Entities
+
+
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/community.johnsnowlabs.com/SaiDeepaPeri/deepa_xlmroberta_ner_large_en_panx_en_4.1.0_3.0_1715017572119.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://community.johnsnowlabs.com/SaiDeepaPeri/deepa_xlmroberta_ner_large_en_panx_en_4.1.0_3.0_1715017572119.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+documentAssembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols(["document"]) \
+    .setOutputCol("token")
+
+token_classifier = XlmRoBertaForTokenClassification.pretrained("deepa_xlmroberta_ner_large_en_panx", "en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("ner")
+
+ner_converter = NerConverter() \
+    .setInputCols(["document", "token", "ner"]) \
+    .setOutputCol("ner_chunk")
+
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, token_classifier, ner_converter])
+
+```
+
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|deepa_xlmroberta_ner_large_en_panx|
+|Compatibility:|Spark NLP 4.1.0+|
+|License:|Open Source|
+|Edition:|Community|
+|Input Labels:|[document, token]|
+|Output Labels:|[ner]|
+|Language:|en|
+|Size:|1.8 GB|
+|Case sensitive:|true|
+|Max sentence length:|256|

docs/_posts/SaiDeepaPeri/2024-05-06-deepa_xlmroberta_ner_large_panx_dataset_en.md

@@ -0,0 +1,78 @@
+---
+layout: model
+title: "Deepa NER XLMRoberta Large Model : deepa_xlmroberta_ner_large_panx"
+author: SaiDeepaPeri
+name: deepa_xlmroberta_ner_large_panx_dataset
+date: 2024-05-06
+tags: [en, open_source]
+task: Named Entity Recognition
+language: en
+edition: Spark NLP 4.1.0
+spark_version: 3.0
+supported: false
+annotator: XlmRoBertaForTokenClassification
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+NER model  XLM Roberta Large Model
+
+## Predicted Entities
+
+
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/community.johnsnowlabs.com/SaiDeepaPeri/deepa_xlmroberta_ner_large_panx_dataset_en_4.1.0_3.0_1715028210601.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://community.johnsnowlabs.com/SaiDeepaPeri/deepa_xlmroberta_ner_large_panx_dataset_en_4.1.0_3.0_1715028210601.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+documentAssembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("document")
+
+# Create a custom Tokenizer that splits text based on spaces
+tokenizer = RegexTokenizer() \
+    .setInputCols(["document"]) \
+    .setOutputCol("token").setPattern("\\s+") \
+
+# deepa_xlmroberta_ner_large_en_panx
+token_classifier = XlmRoBertaForTokenClassification.pretrained("deepa_xlmroberta_ner_large_panx", "en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("ner")
+
+ner_converter = NerConverter() \
+    .setInputCols(["document", "token", "ner"]) \
+    .setOutputCol("ner_chunk")
+
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, token_classifier, ner_converter])
+
+```
+
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|deepa_xlmroberta_ner_large_panx_dataset|
+|Compatibility:|Spark NLP 4.1.0+|
+|License:|Open Source|
+|Edition:|Community|
+|Input Labels:|[document, token]|
+|Output Labels:|[ner]|
+|Language:|en|
+|Size:|1.8 GB|
+|Case sensitive:|true|
+|Max sentence length:|256|

docs/_posts/ahmedlone127/2024-02-11-bge_m3_xx.md

@@ -68,7 +68,7 @@ val sentencerDL = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx
     .setOutputCol("sentence")
 
 val embeddings = XlmRoBertaSentenceEmbeddings 
-    .pretrained("bge_m3", "xx")
+    .pretrained("bge_m3 ", "xx")
     .setInputCols(Array("sentence")) 
     .setOutputCol("embeddings") 
 

docs/_posts/ahmedlone127/2024-06-10-baai_bge_base_english_nowr_1_1_en.md

@@ -0,0 +1,87 @@
+---
+layout: model
+title: English baai_bge_base_english_nowr_1_1 BGEEmbeddings from alexakkol
+author: John Snow Labs
+name: baai_bge_base_english_nowr_1_1
+date: 2024-06-10
+tags: [en, open_source, onnx, embeddings, bge]
+task: Embeddings
+language: en
+edition: Spark NLP 5.4.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BGEEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BGEEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`baai_bge_base_english_nowr_1_1` is a English model originally trained by alexakkol.
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/baai_bge_base_english_nowr_1_1_en_5.4.0_3.0_1718060836858.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/baai_bge_base_english_nowr_1_1_en_5.4.0_3.0_1718060836858.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+
+documentAssembler = DocumentAssembler() \
+      .setInputCol("text") \
+      .setOutputCol("document")
+
+embeddings = BGEEmbeddings.pretrained("baai_bge_base_english_nowr_1_1","en") \
+      .setInputCols(["document"]) \
+      .setOutputCol("embeddings")       
+
+pipeline = Pipeline().setStages([documentAssembler, embeddings])
+data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new DocumentAssembler() 
+    .setInputCol("text") 
+    .setOutputCol("document")
+
+
+val embeddings = BGEEmbeddings.pretrained("baai_bge_base_english_nowr_1_1","en") 
+    .setInputCols(Array("document")) 
+    .setOutputCol("embeddings")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, embeddings))
+val data = Seq("I love spark-nlp).toDS.toDF("text")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|baai_bge_base_english_nowr_1_1|
+|Compatibility:|Spark NLP 5.4.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document]|
+|Output Labels:|[bge]|
+|Language:|en|
+|Size:|381.8 MB|
+
+## References
+
+https://huggingface.co/alexakkol/BAAI-bge-base-en-nowr-1-1

docs/_posts/ahmedlone127/2024-06-10-baai_bge_base_english_nowr_1_1_pipeline_en.md

@@ -0,0 +1,69 @@
+---
+layout: model
+title: English baai_bge_base_english_nowr_1_1_pipeline pipeline BGEEmbeddings from alexakkol
+author: John Snow Labs
+name: baai_bge_base_english_nowr_1_1_pipeline
+date: 2024-06-10
+tags: [en, open_source, pipeline, onnx]
+task: Embeddings
+language: en
+edition: Spark NLP 5.4.0
+spark_version: 3.0
+supported: true
+annotator: PipelineModel
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BGEEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`baai_bge_base_english_nowr_1_1_pipeline` is a English model originally trained by alexakkol.
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/baai_bge_base_english_nowr_1_1_pipeline_en_5.4.0_3.0_1718060870292.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/baai_bge_base_english_nowr_1_1_pipeline_en_5.4.0_3.0_1718060870292.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+
+pipeline = PretrainedPipeline("baai_bge_base_english_nowr_1_1_pipeline", lang = "en")
+annotations =  pipeline.transform(df)   
+
+```
+```scala
+
+val pipeline = new PretrainedPipeline("baai_bge_base_english_nowr_1_1_pipeline", lang = "en")
+val annotations = pipeline.transform(df)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|baai_bge_base_english_nowr_1_1_pipeline|
+|Type:|pipeline|
+|Compatibility:|Spark NLP 5.4.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Language:|en|
+|Size:|381.8 MB|
+
+## References
+
+https://huggingface.co/alexakkol/BAAI-bge-base-en-nowr-1-1
+
+## Included Models
+
+- DocumentAssembler
+- BGEEmbeddings