Multilingual mroberta_pipeline pipeline RoBertaEmbeddings from BSC-LT

Description

Pretrained RoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.mroberta_pipeline is a Multilingual model originally trained by BSC-LT.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("mroberta_pipeline", lang = "xx")
annotations =  pipeline.transform(df)   


val pipeline = new PretrainedPipeline("mroberta_pipeline", lang = "xx")
val annotations = pipeline.transform(df)

Model Information

Model Name: mroberta_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: xx
Size: 553.2 MB

References

https://huggingface.co/BSC-LT/mRoBERTa

Included Models

  • DocumentAssembler
  • TokenizerModel
  • RoBertaEmbeddings