English afriberta_v2_base_pipeline pipeline XlmRoBertaEmbeddings from castorini

Description

Pretrained XlmRoBertaEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.afriberta_v2_base_pipeline is a English model originally trained by castorini.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("afriberta_v2_base_pipeline", lang = "en")
annotations =  pipeline.transform(df)   


val pipeline = new PretrainedPipeline("afriberta_v2_base_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: afriberta_v2_base_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 645.7 MB

References

https://huggingface.co/castorini/afriberta_v2_base

Included Models

  • DocumentAssembler
  • TokenizerModel
  • XlmRoBertaEmbeddings