JohnSnowLabs
diff --git a/‎docs/_posts/Damla-Gurbaz/2023-06-29-xlmroberta_embeddings_paraphrase_mpnet_base_v2_xx.md
+100 b/‎docs/_posts/Damla-Gurbaz/2023-06-29-xlmroberta_embeddings_paraphrase_mpnet_base_v2_xx.md
+100
diff --git a/‎docs/_posts/Mary-Sci/2023-05-28-longformer_base_english_legal_en.md
+97 b/‎docs/_posts/Mary-Sci/2023-05-28-longformer_base_english_legal_en.md
+97
diff --git a/‎docs/_posts/Mary-Sci/2023-05-28-longformer_large_english_legal_en.md
+97 b/‎docs/_posts/Mary-Sci/2023-05-28-longformer_large_english_legal_en.md
+97
diff --git a/‎docs/_posts/Mary-Sci/2023-05-28-xlm_longformer_base_english_legal_en.md
+97 b/‎docs/_posts/Mary-Sci/2023-05-28-xlm_longformer_base_english_legal_en.md
+97
@@ -0,0 +1,100 @@
+---
+layout: model
+title: Multilingual XLMRoBerta Embeddings Cased Model
+author: John Snow Labs
+name: xlmroberta_embeddings_paraphrase_mpnet_base_v2
+date: 2023-06-29
+tags: [xx, embeddings, xlmroberta, open_source, transformer, tensorflow]
+task: Embeddings
+language: xx
+edition: Spark NLP 4.4.4
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: XlmRoBertaEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained XLMRoberta Embeddings model is a multilingual embedding model adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.
+
+## 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/auxdata.johnsnowlabs.com/public/models/xlmroberta_embeddings_paraphrase_mpnet_base_v2_xx_4.4.4_3.0_1688073546075.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/xlmroberta_embeddings_paraphrase_mpnet_base_v2_xx_4.4.4_3.0_1688073546075.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")
+
+embeddings = XlmRoBertaEmbeddings.pretrained("xlmroberta_embeddings_paraphrase_mpnet_base_v2","xx") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings") \
+    .setCaseSensitive(True)
+
+pipeline = Pipeline(stages=[documentAssembler, 
+                            tokenizer, 
+                            embeddings])
+
+data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+      .setInputCol("text") 
+      .setOutputCol("document")
+ 
+val tokenizer = new Tokenizer() 
+    .setInputCols("document")
+    .setOutputCol("token")
+
+val embeddings = XlmRoBertaEmbeddings.pretrained("xlmroberta_embeddings_paraphrase_mpnet_base_v2", "xx") 
+    .setInputCols(Array("document", "token")) 
+    .setOutputCol("embeddings")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, 
+                                              tokenizer, 
+                                              embeddings))
+
+val data = Seq("I love Spark NLP").toDS.toDF("text")
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|xlmroberta_embeddings_paraphrase_mpnet_base_v2|
+|Compatibility:|Spark NLP 4.4.4+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[embeddings]|
+|Language:|xx|
+|Size:|1.0 GB|
+|Case sensitive:|true|
+
+## References
+
+https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2
@@ -0,0 +1,97 @@
+---
+layout: model
+title: English Legal Longformer Base Embeddings Model
+author: John Snow Labs
+name: longformer_base_english_legal
+date: 2023-05-28
+tags: [en, longformerformaskedlm, transformer, open_source, legal, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 4.4.2
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: LongformerEmbeddings
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained Legal Longformer Embeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `legal-longformer-base` is a English model originally trained by `lexlms`.
+
+{:.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/longformer_base_english_legal_en_4.4.2_3.0_1685282124579.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/longformer_base_english_legal_en_4.4.2_3.0_1685282124579.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() \
+    .setInputCols("text") \
+    .setOutputCols("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+
+embeddings = LongformerEmbeddings.pretrained("longformer_base_english_legal","en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings") \
+    .setCaseSensitive(True)
+    
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
+
+data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+    .setInputCols(Array("text")) 
+    .setOutputCols(Array("document"))
+      
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+ 
+val embeddings = LongformerEmbeddings.pretrained("longformer_base_english_legal","en") 
+    .setInputCols(Array("document", "token"))
+    .setOutputCol("embeddings")
+    .setCaseSensitive(True)    
+   
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|longformer_base_english_legal|
+|Compatibility:|Spark NLP 4.4.2+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[embeddings]|
+|Language:|en|
+|Size:|561.6 MB|
+|Case sensitive:|true|
+|Max sentence length:|4096|
+
+## References
+
+https://huggingface.co/lexlms/legal-longformer-base
@@ -0,0 +1,97 @@
+---
+layout: model
+title: English Legal Longformer Large Embeddings Model
+author: John Snow Labs
+name: longformer_large_english_legal
+date: 2023-05-28
+tags: [en, longformerformaskedlm, transformer, open_source, legal, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 4.4.2
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: LongformerEmbeddings
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained Legal Longformer Large Embeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `legal-longformer-large` is a English model originally trained by `lexlms`.
+
+{:.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/longformer_large_english_legal_en_4.4.2_3.0_1685289330980.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/longformer_large_english_legal_en_4.4.2_3.0_1685289330980.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() \
+    .setInputCols("text") \
+    .setOutputCols("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+
+embeddings = LongformerEmbeddings.pretrained("longformer_large_english_legal","en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings") \
+    .setCaseSensitive(True)
+    
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
+
+data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+    .setInputCols(Array("text")) 
+    .setOutputCols(Array("document"))
+      
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+ 
+val embeddings = LongformerEmbeddings.pretrained("longformer_large_english_legal","en") 
+    .setInputCols(Array("document", "token"))
+    .setOutputCol("embeddings")
+    .setCaseSensitive(True)    
+   
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|longformer_large_english_legal|
+|Compatibility:|Spark NLP 4.4.2+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[embeddings]|
+|Language:|en|
+|Size:|1.6 GB|
+|Case sensitive:|true|
+|Max sentence length:|4096|
+
+## References
+
+https://huggingface.co/lexlms/legal-longformer-large
@@ -0,0 +1,97 @@
+---
+layout: model
+title: English Legal XLM-Longformer Base Embeddings Model
+author: John Snow Labs
+name: xlm_longformer_base_english_legal
+date: 2023-05-28
+tags: [en, longformerformaskedlm, transformer, open_source, legal, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 4.4.2
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: LongformerEmbeddings
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained Legal XLM-Longformer Embeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `legal-xlm-longformer-base` is a English model originally trained by `joelito`.
+
+{:.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/xlm_longformer_base_english_legal_en_4.4.2_3.0_1685286936656.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/xlm_longformer_base_english_legal_en_4.4.2_3.0_1685286936656.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() \
+    .setInputCols("text") \
+    .setOutputCols("document")
+
+tokenizer = Tokenizer() \
+    .setInputCols("document") \
+    .setOutputCol("token")
+
+embeddings = LongformerEmbeddings.pretrained("xlm_longformer_base_english_legal","en") \
+    .setInputCols(["document", "token"]) \
+    .setOutputCol("embeddings") \
+    .setCaseSensitive(True)
+    
+pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])
+
+data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+    .setInputCols(Array("text")) 
+    .setOutputCols(Array("document"))
+      
+val tokenizer = new Tokenizer()
+    .setInputCols("document")
+    .setOutputCol("token")
+ 
+val embeddings = LongformerEmbeddings.pretrained("xlm_longformer_base_english_legal","en") 
+    .setInputCols(Array("document", "token"))
+    .setOutputCol("embeddings")
+    .setCaseSensitive(True)    
+   
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))
+
+val data = Seq("I love Spark NLP").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|xlm_longformer_base_english_legal|
+|Compatibility:|Spark NLP 4.4.2+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[embeddings]|
+|Language:|en|
+|Size:|788.6 MB|
+|Case sensitive:|true|
+|Max sentence length:|4096|
+
+## References
+
+https://huggingface.co/joelito/legal-xlm-longformer-base