English oe_roberta_base_mlm_pipeline pipeline RoBertaEmbeddings from Dingyun-Huang

Description

Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.oe_roberta_base_mlm_pipeline is a English model originally trained by Dingyun-Huang.

Download Copy S3 URI

How to use


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


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

Model Information

Model Name: oe_roberta_base_mlm_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 466.4 MB

References

https://huggingface.co/Dingyun-Huang/oe-roberta-base-mlm

Included Models

  • DocumentAssembler
  • TokenizerModel
  • RoBertaEmbeddings