Edit on GitHub
  • John Snow Labs
  • Feb 05, 2025

English obert_3_downstream_pruned_block4_90_squadv1_newmodel_pipeline pipeline BertForQuestionAnswering from tachyon-11

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.obert_3_downstream_pruned_block4_90_squadv1_newmodel_pipeline is a English model originally trained by tachyon-11.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("obert_3_downstream_pruned_block4_90_squadv1_newmodel_pipeline", lang = "en")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("obert_3_downstream_pruned_block4_90_squadv1_newmodel_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: obert_3_downstream_pruned_block4_90_squadv1_newmodel_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 168.7 MB

References

https://huggingface.co/tachyon-11/oBERT-3-downstream-pruned-block4-90-squadv1-newmodel

Included Models

  • MultiDocumentAssembler
  • BertForQuestionAnswering