Edit on GitHub
  • John Snow Labs
  • Sep 17, 2024

Portuguese bert_base_portuguese_cased_finetuned_squadv1_portuguese_pipeline pipeline BertForQuestionAnswering from isel-nlp-mp05

  • pt
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_base_portuguese_cased_finetuned_squadv1_portuguese_pipeline is a Portuguese model originally trained by isel-nlp-mp05.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("bert_base_portuguese_cased_finetuned_squadv1_portuguese_pipeline", lang = "pt")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("bert_base_portuguese_cased_finetuned_squadv1_portuguese_pipeline", lang = "pt")
val annotations = pipeline.transform(df)

Model Information

Model Name: bert_base_portuguese_cased_finetuned_squadv1_portuguese_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: pt
Size: 405.9 MB

References

https://huggingface.co/isel-nlp-mp05/bert-base-portuguese-cased-finetuned-squadv1-pt

Included Models

  • MultiDocumentAssembler
  • BertForQuestionAnswering