English distilbert_base_uncased_becasv2_2 DistilBertForQuestionAnswering from Evelyn18

Description

Pretrained DistilBertForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.distilbert_base_uncased_becasv2_2 is a English model originally trained by Evelyn18.

Download Copy S3 URI

How to use



document_assembler = MultiDocumentAssembler() \
    .setInputCol(["question", "context"]) \
    .setOutputCol(["document_question", "document_context"])
    
    
spanClassifier = DistilBertForQuestionAnswering.pretrained("distilbert_base_uncased_becasv2_2","en") \
            .setInputCols(["document_question","document_context"]) \
            .setOutputCol("answer")

pipeline = Pipeline().setStages([document_assembler, spanClassifier])

pipelineModel = pipeline.fit(data)

pipelineDF = pipelineModel.transform(data)



val document_assembler = new MultiDocumentAssembler()
    .setInputCol(Array("question", "context")) 
    .setOutputCol(Array("document_question", "document_context"))
    
val spanClassifier = DistilBertForQuestionAnswering  
    .pretrained("distilbert_base_uncased_becasv2_2", "en")
    .setInputCols(Array("document_question","document_context")) 
    .setOutputCol("answer") 

val pipeline = new Pipeline().setStages(Array(document_assembler, spanClassifier))

val pipelineModel = pipeline.fit(data)

val pipelineDF = pipelineModel.transform(data)


Model Information

Model Name: distilbert_base_uncased_becasv2_2
Compatibility: Spark NLP 5.2.0+
License: Open Source
Edition: Official
Input Labels: [document_question, document_context]
Output Labels: [answer]
Language: en
Size: 247.2 MB

References

https://huggingface.co/Evelyn18/distilbert-base-uncased-becasv2-2