Models hub (#13943)

* 2023-08-29-mpnet_embedding_tiny_random_mpnet_by_hf_internal_testing_en (#13949) * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnet_by_hf_internal_testing_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetformaskedlm_by_hf_tiny_model_private_en * Add model 2023-08-29-mpnet_embedding_burmese_awesome_setfit_model_en * Add model 2023-08-29-mpnet_embedding_github_issues_mpnet_southern_sotho_e10_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetforquestionanswering_by_hf_tiny_model_private_en * Add model 2023-08-29-mpnet_embedding_multi_qa_mpnet_base_cos_v1_by_navteca_en * Add model 2023-08-29-mpnet_embedding_github_issues_preprocessed_mpnet_southern_sotho_e10_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetfortokenclassification_by_hf_tiny_model_private_en * Add model 2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetforsequenceclassification_by_hf_tiny_model_private_en * Add model 2023-08-29-mpnet_embedding_multi_qa_mpnet_base_cos_v1_by_sentence_transformers_en * Add model 2023-08-29-mpnet_embedding_setfit_alpaca_spanish_unprocessable_sample_detection_es * Add model 2023-08-29-mpnet_embedding_setfit_model_by_rajistics_en * Add model 2023-08-29-mpnet_embedding_multi_qa_mpnet_base_dot_v1_by_sentence_transformers_en * Add model 2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_diptanuc_en * Add model 2023-08-29-mpnet_embedding_setfit_ethos_multilabel_example_by_lewtun_en * Add model 2023-08-29-mpnet_embedding_nli_mpnet_base_v2_by_sentence_transformers_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetforquestionanswering_by_hf_internal_testing_en * Add model 2023-08-29-mpnet_embedding_setfit_model_by_pradipta11_en * Add model 2023-08-29-mpnet_embedding_multi_qa_mpnet_base_dot_v1_by_model_embeddings_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetformaskedlm_by_hf_internal_testing_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetfortokenclassification_by_hf_internal_testing_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetmodel_by_hf_internal_testing_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetmodel_by_hf_tiny_model_private_en * Add model 2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_obrizum_en * Add model 2023-08-29-mpnet_embedding_burmese_awesome_setfit_model_98_en * Add model 2023-08-29-mpnet_embedding_all_mpnet_base_questions_clustering_english_en * Add model 2023-08-29-mpnet_embedding_shona_mpnet_base_snli_mnli_en * Add model 2023-08-29-mpnet_embedding_tiny_random_mpnetforsequenceclassification_by_hf_internal_testing_en * Add model 2023-08-29-mpnet_embedding_setfit_ethos_multilabel_example_by_neilthematic_en * Add model 2023-08-29-mpnet_embedding_paraphrase_mpnet_base_v2_by_sentence_transformers_en --------- Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com> --------- Co-authored-by: jsl-models <74001263+jsl-models@users.noreply.github.com> Co-authored-by: ahmedlone127 <ahmedlone127@gmail.com> Co-authored-by: maziyarpanahi <maziyar.panahi@iscpif.fr>
JohnSnowLabs · Sep 6, 2023 · 543faaf · 543faaf
1 parent 770d5c0
commit 543faaf
Show file tree

Hide file tree

Showing 31 changed files with 2,728 additions and 0 deletions.
diff --git a/...27/2023-08-29-mpnet_embedding_all_mpnet_base_questions_clustering_english_en.md b/...27/2023-08-29-mpnet_embedding_all_mpnet_base_questions_clustering_english_en.md
@@ -0,0 +1,88 @@
+---
+layout: model
+title: English mpnet_embedding_all_mpnet_base_questions_clustering_english TFMPNetModel from aiknowyou
+author: John Snow Labs
+name: mpnet_embedding_all_mpnet_base_questions_clustering_english
+date: 2023-08-29
+tags: [mpnet, en, open_source, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: MPNetEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained mpnet  model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mpnet_embedding_all_mpnet_base_questions_clustering_english` is a English model originally trained by aiknowyou.
+
+{:.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/mpnet_embedding_all_mpnet_base_questions_clustering_english_en_5.1.0_3.0_1693327280583.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mpnet_embedding_all_mpnet_base_questions_clustering_english_en_5.1.0_3.0_1693327280583.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
+
+document_assembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("documents")
+
+instruction = MPNetEmbeddings \
+    .pretrained("mpnet_embedding_all_mpnet_base_questions_clustering_english", "en")\
+    .setInputCols(["documents"]) \
+    .setOutputCol("mpnet_embeddings")
+
+pipeline = Pipeline(stages=[
+  document_assembler,
+  instruction,
+])
+
+pipelineModel = pipeline.fit(data)
+
+pipelineDF = pipelineModel.transform(data)
+```
+```scala
+
+val document_assembler = new DocumentAssembler()
+    .setInputCol("text") 
+    .setOutputCol("documents")
+
+val instruction = MPNetEmbeddings
+    .pretrained("mpnet_embedding_all_mpnet_base_questions_clustering_english", "en")
+    .setInputCols(Array("documents")) 
+    .setOutputCol("mpnet_embeddings") 
+
+val pipeline = new Pipeline().setStages(Array(document_assembler, instruction))
+
+val pipelineModel = pipeline.fit(data)
+
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|mpnet_embedding_all_mpnet_base_questions_clustering_english|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[mpnet_embeddings]|
+|Language:|en|
+|Size:|409.8 MB|
diff --git a/...sts/ahmedlone127/2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_diptanuc_en.md b/...sts/ahmedlone127/2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_diptanuc_en.md
@@ -0,0 +1,88 @@
+---
+layout: model
+title: English mpnet_embedding_all_mpnet_base_v2_by_diptanuc TFMPNetModel from diptanuc
+author: John Snow Labs
+name: mpnet_embedding_all_mpnet_base_v2_by_diptanuc
+date: 2023-08-29
+tags: [mpnet, en, open_source, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: MPNetEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained mpnet  model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mpnet_embedding_all_mpnet_base_v2_by_diptanuc` is a English model originally trained by diptanuc.
+
+{:.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/mpnet_embedding_all_mpnet_base_v2_by_diptanuc_en_5.1.0_3.0_1693326522411.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mpnet_embedding_all_mpnet_base_v2_by_diptanuc_en_5.1.0_3.0_1693326522411.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
+
+document_assembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("documents")
+
+instruction = MPNetEmbeddings \
+    .pretrained("mpnet_embedding_all_mpnet_base_v2_by_diptanuc", "en")\
+    .setInputCols(["documents"]) \
+    .setOutputCol("mpnet_embeddings")
+
+pipeline = Pipeline(stages=[
+  document_assembler,
+  instruction,
+])
+
+pipelineModel = pipeline.fit(data)
+
+pipelineDF = pipelineModel.transform(data)
+```
+```scala
+
+val document_assembler = new DocumentAssembler()
+    .setInputCol("text") 
+    .setOutputCol("documents")
+
+val instruction = MPNetEmbeddings
+    .pretrained("mpnet_embedding_all_mpnet_base_v2_by_diptanuc", "en")
+    .setInputCols(Array("documents")) 
+    .setOutputCol("mpnet_embeddings") 
+
+val pipeline = new Pipeline().setStages(Array(document_assembler, instruction))
+
+val pipelineModel = pipeline.fit(data)
+
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|mpnet_embedding_all_mpnet_base_v2_by_diptanuc|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[mpnet_embeddings]|
+|Language:|en|
+|Size:|409.6 MB|
diff --git a/...osts/ahmedlone127/2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_obrizum_en.md b/...osts/ahmedlone127/2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_obrizum_en.md
@@ -0,0 +1,88 @@
+---
+layout: model
+title: English mpnet_embedding_all_mpnet_base_v2_by_obrizum TFMPNetModel from obrizum
+author: John Snow Labs
+name: mpnet_embedding_all_mpnet_base_v2_by_obrizum
+date: 2023-08-29
+tags: [mpnet, en, open_source, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: MPNetEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained mpnet  model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mpnet_embedding_all_mpnet_base_v2_by_obrizum` is a English model originally trained by obrizum.
+
+{:.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/mpnet_embedding_all_mpnet_base_v2_by_obrizum_en_5.1.0_3.0_1693327114140.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mpnet_embedding_all_mpnet_base_v2_by_obrizum_en_5.1.0_3.0_1693327114140.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
+
+document_assembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("documents")
+
+instruction = MPNetEmbeddings \
+    .pretrained("mpnet_embedding_all_mpnet_base_v2_by_obrizum", "en")\
+    .setInputCols(["documents"]) \
+    .setOutputCol("mpnet_embeddings")
+
+pipeline = Pipeline(stages=[
+  document_assembler,
+  instruction,
+])
+
+pipelineModel = pipeline.fit(data)
+
+pipelineDF = pipelineModel.transform(data)
+```
+```scala
+
+val document_assembler = new DocumentAssembler()
+    .setInputCol("text") 
+    .setOutputCol("documents")
+
+val instruction = MPNetEmbeddings
+    .pretrained("mpnet_embedding_all_mpnet_base_v2_by_obrizum", "en")
+    .setInputCols(Array("documents")) 
+    .setOutputCol("mpnet_embeddings") 
+
+val pipeline = new Pipeline().setStages(Array(document_assembler, instruction))
+
+val pipelineModel = pipeline.fit(data)
+
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|mpnet_embedding_all_mpnet_base_v2_by_obrizum|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[mpnet_embeddings]|
+|Language:|en|
+|Size:|409.6 MB|
diff --git a/...127/2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers_en.md b/...127/2023-08-29-mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers_en.md
@@ -0,0 +1,88 @@
+---
+layout: model
+title: English mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers TFMPNetModel from sentence-transformers
+author: John Snow Labs
+name: mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers
+date: 2023-08-29
+tags: [mpnet, en, open_source, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: MPNetEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained mpnet  model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers` is a English model originally trained by sentence-transformers.
+
+{:.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/mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers_en_5.1.0_3.0_1693326097073.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers_en_5.1.0_3.0_1693326097073.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
+
+document_assembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("documents")
+
+instruction = MPNetEmbeddings \
+    .pretrained("mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers", "en")\
+    .setInputCols(["documents"]) \
+    .setOutputCol("mpnet_embeddings")
+
+pipeline = Pipeline(stages=[
+  document_assembler,
+  instruction,
+])
+
+pipelineModel = pipeline.fit(data)
+
+pipelineDF = pipelineModel.transform(data)
+```
+```scala
+
+val document_assembler = new DocumentAssembler()
+    .setInputCol("text") 
+    .setOutputCol("documents")
+
+val instruction = MPNetEmbeddings
+    .pretrained("mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers", "en")
+    .setInputCols(Array("documents")) 
+    .setOutputCol("mpnet_embeddings") 
+
+val pipeline = new Pipeline().setStages(Array(document_assembler, instruction))
+
+val pipelineModel = pipeline.fit(data)
+
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|mpnet_embedding_all_mpnet_base_v2_by_sentence_transformers|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[mpnet_embeddings]|
+|Language:|en|
+|Size:|409.6 MB|