English fin_mpnet_base_pipeline pipeline MPNetEmbeddings from mukaj

Description

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

Predicted Entities

Download Copy S3 URI

How to use

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

Model Information

Model Name: fin_mpnet_base_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 407.0 MB

References

References

https://huggingface.co/mukaj/fin-mpnet-base

Included Models

  • DocumentAssembler
  • MPNetEmbeddings