Edit on GitHub
  • John Snow Labs
  • Sep 17, 2024

Arabic qa_finetuned_distilbert_based_uncased_pipeline pipeline DistilBertForQuestionAnswering from gp-tar4

  • ar
  • open_source
  • pipeline
  • onnx

Description

Pretrained DistilBertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.qa_finetuned_distilbert_based_uncased_pipeline is a Arabic model originally trained by gp-tar4.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("qa_finetuned_distilbert_based_uncased_pipeline", lang = "ar")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("qa_finetuned_distilbert_based_uncased_pipeline", lang = "ar")
val annotations = pipeline.transform(df)

Model Information

Model Name: qa_finetuned_distilbert_based_uncased_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: ar
Size: 243.8 MB

References

https://huggingface.co/gp-tar4/QA_FineTuned_DistilBert-based-uncased

Included Models

  • MultiDocumentAssembler
  • DistilBertForQuestionAnswering