English bert_base_cased_wikitext2_klee_9_pipeline pipeline BertEmbeddings from klee-9

Description

Pretrained BertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_base_cased_wikitext2_klee_9_pipeline is a English model originally trained by klee-9.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("bert_base_cased_wikitext2_klee_9_pipeline", lang = "en")
annotations =  pipeline.transform(df)   


val pipeline = new PretrainedPipeline("bert_base_cased_wikitext2_klee_9_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: bert_base_cased_wikitext2_klee_9_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 403.5 MB

References

https://huggingface.co/klee-9/bert-base-cased-wikitext2

Included Models

  • DocumentAssembler
  • TokenizerModel
  • BertEmbeddings