Edit on GitHub
  • John Snow Labs
  • Jan 26, 2025

English babylm_roberta_base_epoch_20_pipeline pipeline RoBertaEmbeddings from Raj-Sanjay-Shah

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.babylm_roberta_base_epoch_20_pipeline is a English model originally trained by Raj-Sanjay-Shah.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("babylm_roberta_base_epoch_20_pipeline", lang = "en")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("babylm_roberta_base_epoch_20_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: babylm_roberta_base_epoch_20_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 465.7 MB

References

https://huggingface.co/Raj-Sanjay-Shah/babyLM_roberta_base_epoch_20

Included Models

  • DocumentAssembler
  • TokenizerModel
  • RoBertaEmbeddings