Edit on GitHub
  • John Snow Labs
  • Aug 02, 2024

English t5_doc2query_base_msmarco_pipeline pipeline T5Transformer from macavaney

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.t5_doc2query_base_msmarco_pipeline is a English model originally trained by macavaney.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("t5_doc2query_base_msmarco_pipeline", lang = "en")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("t5_doc2query_base_msmarco_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: t5_doc2query_base_msmarco_pipeline
Type: pipeline
Compatibility: Spark NLP 5.4.2+
License: Open Source
Edition: Official
Language: en
Size: 520.8 MB

References

https://huggingface.co/macavaney/doc2query-t5-base-msmarco

Included Models

  • DocumentAssembler
  • T5Transformer