2023-11-15-bert_qa_base_uncased_few_shot_k_16_finetuned_squad_seed_2_en

docs/_posts/ahmedlone127/2023-11-15-bert_qa_base_multilingual_cased_finetuned_viquad_en.md

@@ -0,0 +1,100 @@
+---
+layout: model
+title: English BertForQuestionAnswering Base Cased model (from Khanh)
+author: John Snow Labs
+name: bert_qa_base_multilingual_cased_finetuned_viquad
+date: 2023-11-15
+tags: [en, open_source, bert, question_answering, onnx]
+task: Question Answering
+language: en
+edition: Spark NLP 5.2.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BertForQuestionAnswering
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-multilingual-cased-finetuned-viquad` is a English model originally trained by `Khanh`.
+
+## 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/bert_qa_base_multilingual_cased_finetuned_viquad_en_5.2.0_3.0_1700058664073.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_qa_base_multilingual_cased_finetuned_viquad_en_5.2.0_3.0_1700058664073.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 = MultiDocumentAssembler() \
+    .setInputCols(["question", "context"]) \
+    .setOutputCols(["document_question", "document_context"])
+
+spanClassifier = BertForQuestionAnswering.pretrained("bert_qa_base_multilingual_cased_finetuned_viquad","en") \
+    .setInputCols(["document_question", "document_context"]) \
+    .setOutputCol("answer")\
+    .setCaseSensitive(True)
+
+pipeline = Pipeline(stages=[documentAssembler, spanClassifier])
+
+data = spark.createDataFrame([["What is my name?", "My name is Clara and I live in Berkeley."]]).toDF("question", "context")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val documentAssembler = new MultiDocumentAssembler() 
+      .setInputCols(Array("question", "context")) 
+      .setOutputCols(Array("document_question", "document_context"))
+
+val spanClassifer = BertForQuestionAnswering.pretrained("bert_qa_base_multilingual_cased_finetuned_viquad","en") 
+    .setInputCols(Array("document", "token")) 
+    .setOutputCol("answer")
+    .setCaseSensitive(true)
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, spanClassifier))
+
+val data = Seq("What is my name?", "My name is Clara and I live in Berkeley.").toDF("question", "context")
+
+val result = pipeline.fit(data).transform(data)
+```
+
+{:.nlu-block}
+```python
+import nlu
+nlu.load("en.answer_question.bert.cased_multilingual_base_finetuned").predict("""What is my name?|||"My name is Clara and I live in Berkeley.""")
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_qa_base_multilingual_cased_finetuned_viquad|
+|Compatibility:|Spark NLP 5.2.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document_question, document_context]|
+|Output Labels:|[answer]|
+|Language:|en|
+|Size:|665.0 MB|
+|Case sensitive:|true|
+|Max sentence length:|512|
+
+## References
+
+References
+
+- https://huggingface.co/Khanh/bert-base-multilingual-cased-finetuned-viquad

docs/_posts/ahmedlone127/2023-11-15-bert_qa_base_multilingual_cased_finetuned_xx.md

@@ -0,0 +1,94 @@
+---
+layout: model
+title: Multilingual BertForQuestionAnswering Base Cased model (from obokkkk)
+author: John Snow Labs
+name: bert_qa_base_multilingual_cased_finetuned
+date: 2023-11-15
+tags: [xx, open_source, bert, question_answering, onnx]
+task: Question Answering
+language: xx
+edition: Spark NLP 5.2.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BertForQuestionAnswering
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BertForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-multilingual-cased-finetuned` is a Multilingual model originally trained by `obokkkk`.
+
+## 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/bert_qa_base_multilingual_cased_finetuned_xx_5.2.0_3.0_1700058641683.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_qa_base_multilingual_cased_finetuned_xx_5.2.0_3.0_1700058641683.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 = MultiDocumentAssembler()\
+     .setInputCols(["question", "context"])\
+     .setOutputCols(["document_question", "document_context"])
+
+Question_Answering = BertForQuestionAnswering.pretrained("bert_qa_base_multilingual_cased_finetuned","xx")\
+     .setInputCols(["document_question", "document_context"])\
+     .setOutputCol("answer")\
+     .setCaseSensitive(True)
+
+pipeline = Pipeline(stages=[Document_Assembler, Question_Answering])
+
+data = spark.createDataFrame([["What's my name?","My name is Clara and I live in Berkeley."]]).toDF("question", "context")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val Document_Assembler = new MultiDocumentAssembler()
+     .setInputCols(Array("question", "context"))
+     .setOutputCols(Array("document_question", "document_context"))
+
+val Question_Answering = BertForQuestionAnswering.pretrained("bert_qa_base_multilingual_cased_finetuned","xx")
+     .setInputCols(Array("document_question", "document_context"))
+     .setOutputCol("answer")
+     .setCaseSensitive(true)
+
+val pipeline = new Pipeline().setStages(Array(Document_Assembler, Question_Answering))
+
+val data = Seq("What's my name?","My name is Clara and I live in Berkeley.").toDS.toDF("question", "context")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_qa_base_multilingual_cased_finetuned|
+|Compatibility:|Spark NLP 5.2.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document_question, document_context]|
+|Output Labels:|[answer]|
+|Language:|xx|
+|Size:|665.0 MB|
+|Case sensitive:|true|
+|Max sentence length:|512|
+
+## References
+
+References
+
+- https://huggingface.co/obokkkk/bert-base-multilingual-cased-finetuned

docs/_posts/ahmedlone127/2023-11-15-bert_qa_base_multilingual_uncased_finetuned_squadv2_xx.md

@@ -0,0 +1,94 @@
+---
+layout: model
+title: Multilingual BertForQuestionAnswering Base Uncased model (from khoanvm)
+author: John Snow Labs
+name: bert_qa_base_multilingual_uncased_finetuned_squadv2
+date: 2023-11-15
+tags: [xx, open_source, bert, question_answering, onnx]
+task: Question Answering
+language: xx
+edition: Spark NLP 5.2.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BertForQuestionAnswering
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BertForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-multilingual-uncased-finetuned-squadv2` is a Multilingual model originally trained by `khoanvm`.
+
+## 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/bert_qa_base_multilingual_uncased_finetuned_squadv2_xx_5.2.0_3.0_1700059023790.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_qa_base_multilingual_uncased_finetuned_squadv2_xx_5.2.0_3.0_1700059023790.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 = MultiDocumentAssembler()\
+     .setInputCols(["question", "context"])\
+     .setOutputCols(["document_question", "document_context"])
+
+Question_Answering = BertForQuestionAnswering.pretrained("bert_qa_base_multilingual_uncased_finetuned_squadv2","xx")\
+     .setInputCols(["document_question", "document_context"])\
+     .setOutputCol("answer")\
+     .setCaseSensitive(True)
+
+pipeline = Pipeline(stages=[Document_Assembler, Question_Answering])
+
+data = spark.createDataFrame([["What's my name?","My name is Clara and I live in Berkeley."]]).toDF("question", "context")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val Document_Assembler = new MultiDocumentAssembler()
+     .setInputCols(Array("question", "context"))
+     .setOutputCols(Array("document_question", "document_context"))
+
+val Question_Answering = BertForQuestionAnswering.pretrained("bert_qa_base_multilingual_uncased_finetuned_squadv2","xx")
+     .setInputCols(Array("document_question", "document_context"))
+     .setOutputCol("answer")
+     .setCaseSensitive(true)
+
+val pipeline = new Pipeline().setStages(Array(Document_Assembler, Question_Answering))
+
+val data = Seq("What's my name?","My name is Clara and I live in Berkeley.").toDS.toDF("question", "context")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_qa_base_multilingual_uncased_finetuned_squadv2|
+|Compatibility:|Spark NLP 5.2.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document_question, document_context]|
+|Output Labels:|[answer]|
+|Language:|xx|
+|Size:|625.5 MB|
+|Case sensitive:|false|
+|Max sentence length:|512|
+
+## References
+
+References
+
+- https://huggingface.co/khoanvm/bert-base-multilingual-uncased-finetuned-squadv2

docs/_posts/ahmedlone127/2023-11-15-bert_qa_base_nnish_cased_squad1_fi.md

@@ -0,0 +1,96 @@
+---
+layout: model
+title: Finnish BertForQuestionAnswering Base Cased model (from ilmariky)
+author: John Snow Labs
+name: bert_qa_base_nnish_cased_squad1
+date: 2023-11-15
+tags: [fi, open_source, bert, question_answering, onnx]
+task: Question Answering
+language: fi
+edition: Spark NLP 5.2.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: BertForQuestionAnswering
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained BertForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. `bert-base-finnish-cased-squad1-fi` is a Finnish model originally trained by `ilmariky`.
+
+## 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/bert_qa_base_nnish_cased_squad1_fi_5.2.0_3.0_1700058973995.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/bert_qa_base_nnish_cased_squad1_fi_5.2.0_3.0_1700058973995.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 = MultiDocumentAssembler()\
+     .setInputCols(["question", "context"])\
+     .setOutputCols(["document_question", "document_context"])
+
+Question_Answering = BertForQuestionAnswering.pretrained("bert_qa_base_nnish_cased_squad1","fi")\
+     .setInputCols(["document_question", "document_context"])\
+     .setOutputCol("answer")\
+     .setCaseSensitive(True)
+
+pipeline = Pipeline(stages=[Document_Assembler, Question_Answering])
+
+data = spark.createDataFrame([["What's my name?","My name is Clara and I live in Berkeley."]]).toDF("question", "context")
+
+result = pipeline.fit(data).transform(data)
+```
+```scala
+val Document_Assembler = new MultiDocumentAssembler()
+     .setInputCols(Array("question", "context"))
+     .setOutputCols(Array("document_question", "document_context"))
+
+val Question_Answering = BertForQuestionAnswering.pretrained("bert_qa_base_nnish_cased_squad1","fi")
+     .setInputCols(Array("document_question", "document_context"))
+     .setOutputCol("answer")
+     .setCaseSensitive(true)
+
+val pipeline = new Pipeline().setStages(Array(Document_Assembler, Question_Answering))
+
+val data = Seq("What's my name?","My name is Clara and I live in Berkeley.").toDS.toDF("question", "context")
+
+val result = pipeline.fit(data).transform(data)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|bert_qa_base_nnish_cased_squad1|
+|Compatibility:|Spark NLP 5.2.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document_question, document_context]|
+|Output Labels:|[answer]|
+|Language:|fi|
+|Size:|464.7 MB|
+|Case sensitive:|true|
+|Max sentence length:|512|
+
+## References
+
+References
+
+- https://huggingface.co/ilmariky/bert-base-finnish-cased-squad1-fi
+- https://github.com/google-research-datasets/tydiqa
+- https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/