Edit on GitHub
  • John Snow Labs
  • Aug 16, 2024

English mt5_base_trimmed_russian_90000_pipeline pipeline T5Transformer from research-backup

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained T5Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.mt5_base_trimmed_russian_90000_pipeline is a English model originally trained by research-backup.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("mt5_base_trimmed_russian_90000_pipeline", lang = "en")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("mt5_base_trimmed_russian_90000_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: mt5_base_trimmed_russian_90000_pipeline
Type: pipeline
Compatibility: Spark NLP 5.4.2+
License: Open Source
Edition: Official
Language: en
Size: 777.6 MB

References

https://huggingface.co/research-backup/mt5-base-trimmed-ru-90000

Included Models

  • DocumentAssembler
  • T5Transformer