2024-09-07-fine_tuned_distilbert_pipeline_en

docs/_posts/ahmedlone127/2024-09-01-roberta_finetuned_subjqa_movies_2_mustafa1923_en.md

@@ -0,0 +1,86 @@
+---
+layout: model
+title: English roberta_finetuned_subjqa_movies_2_mustafa1923 RoBertaForQuestionAnswering from mustafa1923
+author: John Snow Labs
+name: roberta_finetuned_subjqa_movies_2_mustafa1923
+date: 2024-09-01
+tags: [en, open_source, onnx, question_answering, roberta]
+task: Question Answering
+language: en
+edition: Spark NLP 5.4.2
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: RoBertaForQuestionAnswering
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained RoBertaForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`roberta_finetuned_subjqa_movies_2_mustafa1923` is a English model originally trained by mustafa1923.
+
+{:.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/roberta_finetuned_subjqa_movies_2_mustafa1923_en_5.4.2_3.0_1725206868726.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/roberta_finetuned_subjqa_movies_2_mustafa1923_en_5.4.2_3.0_1725206868726.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() \
+     .setInputCol(["question", "context"]) \
+     .setOutputCol(["document_question", "document_context"])
+
+spanClassifier = RoBertaForQuestionAnswering.pretrained("roberta_finetuned_subjqa_movies_2_mustafa1923","en") \
+     .setInputCols(["document_question","document_context"]) \
+     .setOutputCol("answer")
+
+pipeline = Pipeline().setStages([documentAssembler, spanClassifier])
+data = spark.createDataFrame([["What framework do I use?","I use spark-nlp."]]).toDF("document_question", "document_context")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new MultiDocumentAssembler()
+    .setInputCol(Array("question", "context")) 
+    .setOutputCol(Array("document_question", "document_context"))
+
+val spanClassifier = RoBertaForQuestionAnswering.pretrained("roberta_finetuned_subjqa_movies_2_mustafa1923", "en")
+    .setInputCols(Array("document_question","document_context")) 
+    .setOutputCol("answer") 
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, spanClassifier))
+val data = Seq("What framework do I use?","I use spark-nlp.").toDS.toDF("document_question", "document_context")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|roberta_finetuned_subjqa_movies_2_mustafa1923|
+|Compatibility:|Spark NLP 5.4.2+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document_question, document_context]|
+|Output Labels:|[answer]|
+|Language:|en|
+|Size:|464.1 MB|
+
+## References
+
+https://huggingface.co/mustafa1923/roberta-finetuned-subjqa-movies_2

docs/_posts/ahmedlone127/2024-09-02-finetuning_sentiment_model_3000_samples_vishalpanda10_en.md

@@ -0,0 +1,94 @@
+---
+layout: model
+title: English finetuning_sentiment_model_3000_samples_vishalpanda10 DistilBertForSequenceClassification from vishalpanda10
+author: John Snow Labs
+name: finetuning_sentiment_model_3000_samples_vishalpanda10
+date: 2024-09-02
+tags: [en, open_source, onnx, sequence_classification, distilbert]
+task: Text Classification
+language: en
+edition: Spark NLP 5.5.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: DistilBertForSequenceClassification
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained DistilBertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`finetuning_sentiment_model_3000_samples_vishalpanda10` is a English model originally trained by vishalpanda10.
+
+{:.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/finetuning_sentiment_model_3000_samples_vishalpanda10_en_5.5.0_3.0_1725305707642.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/finetuning_sentiment_model_3000_samples_vishalpanda10_en_5.5.0_3.0_1725305707642.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')
+
+sequenceClassifier  = DistilBertForSequenceClassification.pretrained("finetuning_sentiment_model_3000_samples_vishalpanda10","en") \
+     .setInputCols(["documents","token"]) \
+     .setOutputCol("class")
+
+pipeline = Pipeline().setStages([documentAssembler, tokenizer, sequenceClassifier])
+data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new DocumentAssembler()
+    .setInputCols("text")
+    .setOutputCols("document")
+
+val tokenizer = new Tokenizer()
+    .setInputCols(Array("document"))
+    .setOutputCol("token")
+
+val sequenceClassifier = DistilBertForSequenceClassification.pretrained("finetuning_sentiment_model_3000_samples_vishalpanda10", "en")
+    .setInputCols(Array("documents","token")) 
+    .setOutputCol("class") 
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, sequenceClassifier))
+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:|finetuning_sentiment_model_3000_samples_vishalpanda10|
+|Compatibility:|Spark NLP 5.5.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document, token]|
+|Output Labels:|[class]|
+|Language:|en|
+|Size:|249.5 MB|
+
+## References
+
+https://huggingface.co/vishalpanda10/finetuning-sentiment-model-3000-samples

docs/_posts/ahmedlone127/2024-09-03-albert_base_qa_2_k_fold_2_en.md

@@ -0,0 +1,86 @@
+---
+layout: model
+title: English albert_base_qa_2_k_fold_2 AlbertForQuestionAnswering from mateiaass
+author: John Snow Labs
+name: albert_base_qa_2_k_fold_2
+date: 2024-09-03
+tags: [en, open_source, onnx, question_answering, albert]
+task: Question Answering
+language: en
+edition: Spark NLP 5.5.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: AlbertForQuestionAnswering
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained AlbertForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`albert_base_qa_2_k_fold_2` is a English model originally trained by mateiaass.
+
+{:.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/albert_base_qa_2_k_fold_2_en_5.5.0_3.0_1725341906099.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/albert_base_qa_2_k_fold_2_en_5.5.0_3.0_1725341906099.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() \
+     .setInputCol(["question", "context"]) \
+     .setOutputCol(["document_question", "document_context"])
+
+spanClassifier = AlbertForQuestionAnswering.pretrained("albert_base_qa_2_k_fold_2","en") \
+     .setInputCols(["document_question","document_context"]) \
+     .setOutputCol("answer")
+
+pipeline = Pipeline().setStages([documentAssembler, spanClassifier])
+data = spark.createDataFrame([["What framework do I use?","I use spark-nlp."]]).toDF("document_question", "document_context")
+pipelineModel = pipeline.fit(data)
+pipelineDF = pipelineModel.transform(data)
+
+```
+```scala
+
+val documentAssembler = new MultiDocumentAssembler()
+    .setInputCol(Array("question", "context")) 
+    .setOutputCol(Array("document_question", "document_context"))
+
+val spanClassifier = AlbertForQuestionAnswering.pretrained("albert_base_qa_2_k_fold_2", "en")
+    .setInputCols(Array("document_question","document_context")) 
+    .setOutputCol("answer") 
+
+val pipeline = new Pipeline().setStages(Array(documentAssembler, spanClassifier))
+val data = Seq("What framework do I use?","I use spark-nlp.").toDS.toDF("document_question", "document_context")
+val pipelineModel = pipeline.fit(data)
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|albert_base_qa_2_k_fold_2|
+|Compatibility:|Spark NLP 5.5.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[document_question, document_context]|
+|Output Labels:|[answer]|
+|Language:|en|
+|Size:|42.0 MB|
+
+## References
+
+https://huggingface.co/mateiaass/albert-base-qa-2-k-fold-2

docs/_posts/ahmedlone127/2024-09-03-cultural_heritage_metadata_accuracy_mnli_pipeline_en.md

@@ -0,0 +1,70 @@
+---
+layout: model
+title: English cultural_heritage_metadata_accuracy_mnli_pipeline pipeline XlmRoBertaForSequenceClassification from davanstrien
+author: John Snow Labs
+name: cultural_heritage_metadata_accuracy_mnli_pipeline
+date: 2024-09-03
+tags: [en, open_source, pipeline, onnx]
+task: Text Classification
+language: en
+edition: Spark NLP 5.5.0
+spark_version: 3.0
+supported: true
+annotator: PipelineModel
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained XlmRoBertaForSequenceClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`cultural_heritage_metadata_accuracy_mnli_pipeline` is a English model originally trained by davanstrien.
+
+{:.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/cultural_heritage_metadata_accuracy_mnli_pipeline_en_5.5.0_3.0_1725396428724.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/cultural_heritage_metadata_accuracy_mnli_pipeline_en_5.5.0_3.0_1725396428724.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("cultural_heritage_metadata_accuracy_mnli_pipeline", lang = "en")
+annotations =  pipeline.transform(df)   
+
+```
+```scala
+
+val pipeline = new PretrainedPipeline("cultural_heritage_metadata_accuracy_mnli_pipeline", lang = "en")
+val annotations = pipeline.transform(df)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|cultural_heritage_metadata_accuracy_mnli_pipeline|
+|Type:|pipeline|
+|Compatibility:|Spark NLP 5.5.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Language:|en|
+|Size:|807.5 MB|
+
+## References
+
+https://huggingface.co/davanstrien/cultural_heritage_metadata_accuracy_mnli
+
+## Included Models
+
+- DocumentAssembler
+- TokenizerModel
+- XlmRoBertaForSequenceClassification