Models hub (#13651)

---------

Co-authored-by: gokhanturer <mgturer@gmail.com>

---------

Co-authored-by: gadde5300 <gadde5300@gmail.com>
Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com>
Co-authored-by: gokhanturer <mgturer@gmail.com>
Co-authored-by: Mary-Sci <meryemyildiz366@gmail.com>
Co-authored-by: Meryem1425 <vildansarikaya25@gmail.com>
Co-authored-by: Vildan <64216738+Meryem1425@users.noreply.github.com>
Co-authored-by: Cabir40 <cabir4006@gmail.com>
Co-authored-by: Merve Ertas Uslu <67653613+Mary-Sci@users.noreply.github.com>
Co-authored-by: Zhengyi-Xiao <zxiao@fandm.edu>

docs/_posts/Cabir40/2023-03-01-t5_flan_base_samsum_en.md

@@ -0,0 +1,84 @@
+---
+layout: model
+title: English T5ForConditionalGeneration Cased model (from philschmid)
+author: John Snow Labs
+name: t5_flan_base_samsum
+date: 2023-03-01
+tags: [open_source, t5, flan, en, tensorflow]
+task: Text Generation
+language: en
+edition: Spark NLP 4.3.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: T5Transformer
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. flan-t5-base-samsum is a English model originally trained by philschmid.
+
+{:.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/t5_flan_base_samsum_en_4.3.0_3.0_1677705397088.zip){:.button.button-orange}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/t5_flan_base_samsum_en_4.3.0_3.0_1677705397088.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")
+
+t5 = T5Transformer.pretrained("t5_flan_base_samsum","en") \
+.setInputCols("document") \
+.setOutputCol("answers")
+
+pipeline = Pipeline(stages=[documentAssembler, t5])
+
+data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+.setInputCols("text")
+.setOutputCols("document")
+
+val t5 = T5Transformer.pretrained("t5_flan_base_samsum","en") 
+.setInputCols("document")
+.setOutputCol("answers")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))
+
+val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|t5_flan_base_samsum|
+|Compatibility:|Spark NLP 4.3.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[t5]|
+|Language:|en|
+|Size:|1.0 GB|
+
+## References
+
+https://huggingface.co/philschmid/flan-t5-base-samsum

docs/_posts/Cabir40/2023-03-01-t5_flan_base_xx.md

@@ -0,0 +1,84 @@
+---
+layout: model
+title: English T5ForConditionalGeneration Cased model (from google)
+author: John Snow Labs
+name: t5_flan_base
+date: 2023-03-01
+tags: [open_source, t5, flan, xx, tensorflow]
+task: Text Generation
+language: xx
+edition: Spark NLP 4.3.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: T5Transformer
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. flan-t5-base is a English model originally trained by google.
+
+{:.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/t5_flan_base_xx_4.3.0_3.0_1677702524850.zip){:.button.button-orange}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/t5_flan_base_xx_4.3.0_3.0_1677702524850.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")
+
+t5 = T5Transformer.pretrained("t5_flan_base","xx") \
+.setInputCols("document") \
+.setOutputCol("answers")
+
+pipeline = Pipeline(stages=[documentAssembler, t5])
+
+data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+.setInputCols("text")
+.setOutputCols("document")
+
+val t5 = T5Transformer.pretrained("t5_flan_base","xx") 
+.setInputCols("document")
+.setOutputCol("answers")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))
+
+val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|t5_flan_base|
+|Compatibility:|Spark NLP 4.3.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[t5]|
+|Language:|xx|
+|Size:|1.0 GB|
+
+## References
+
+https://huggingface.co/google/flan-t5-base

docs/_posts/Cabir40/2023-03-02-t5_flan_base_tldr_news_en.md

@@ -0,0 +1,84 @@
+---
+layout: model
+title: English T5ForConditionalGeneration Cased model (from ybagoury)
+author: John Snow Labs
+name: t5_flan_base_tldr_news
+date: 2023-03-02
+tags: [open_source, t5, flan, en, tensorflow]
+task: Text Generation
+language: en
+edition: Spark NLP 4.3.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: T5Transformer
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. flan-t5-base-tldr_news is a English model originally trained by ybagoury.
+
+{:.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/t5_flan_base_tldr_news_en_4.3.0_3.0_1677760144575.zip){:.button.button-orange}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/t5_flan_base_tldr_news_en_4.3.0_3.0_1677760144575.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")
+
+t5 = T5Transformer.pretrained("t5_flan_base_tldr_news","en") \
+.setInputCols("document") \
+.setOutputCol("answers")
+
+pipeline = Pipeline(stages=[documentAssembler, t5])
+
+data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new DocumentAssembler() 
+.setInputCols("text")
+.setOutputCols("document")
+
+val t5 = T5Transformer.pretrained("t5_flan_base_tldr_news","en") 
+.setInputCols("document")
+.setOutputCol("answers")
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))
+
+val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|t5_flan_base_tldr_news|
+|Compatibility:|Spark NLP 4.3.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[t5]|
+|Language:|en|
+|Size:|1.0 GB|
+
+## References
+
+https://huggingface.co/ybagoury/flan-t5-base-tldr_news

docs/_posts/Mary-Sci/2023-03-12-deberta_embeddings_cowese_base_es.md

@@ -0,0 +1,96 @@
+---
+layout: model
+title: Spanish Deberta Embeddings model (from plncmm)
+author: John Snow Labs
+name: deberta_embeddings_cowese_base
+date: 2023-03-12
+tags: [deberta, open_source, deberta_embeddings, debertav2formaskedlm, es, tensorflow]
+task: Embeddings
+language: es
+edition: Spark NLP 4.3.1
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: DeBertaEmbeddings
+article_header:
+type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained DebertaEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `mdeberta-cowese-base-es` is a Spanish model originally trained by `plncmm`.
+
+{:.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/deberta_embeddings_cowese_base_es_4.3.1_3.0_1678657528702.zip){:.button.button-orange}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/deberta_embeddings_cowese_base_es_4.3.1_3.0_1678657528702.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 = DeBertaEmbeddings.pretrained("deberta_embeddings_cowese_base","es") \
+    .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 = DeBertaEmbeddings.pretrained("deberta_embeddings_cowese_base","es") 
+    .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:|deberta_embeddings_cowese_base|
+|Compatibility:|Spark NLP 4.3.1+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[sentence, token]|
+|Output Labels:|[embeddings]|
+|Language:|es|
+|Size:|1.0 GB|
+|Case sensitive:|false|
+
+## References
+
+https://huggingface.co/plncmm/mdeberta-cowese-base-es