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

Hebrew dictabert_large_heq_pipeline pipeline BertForQuestionAnswering from dicta-il

  • he
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.dictabert_large_heq_pipeline is a Hebrew model originally trained by dicta-il.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("dictabert_large_heq_pipeline", lang = "he")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("dictabert_large_heq_pipeline", lang = "he")
val annotations = pipeline.transform(df)

Model Information

Model Name: dictabert_large_heq_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: he
Size: 1.6 GB

References

https://huggingface.co/dicta-il/dictabert-large-heq

Included Models

  • MultiDocumentAssembler
  • BertForQuestionAnswering