Edit on GitHub
  • John Snow Labs
  • Feb 08, 2025

English gpt_2_340m_distilled_promptkd_dolly_v1_0_pipeline pipeline GPT2Transformer from gmkim

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained GPT2Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.gpt_2_340m_distilled_promptkd_dolly_v1_0_pipeline is a English model originally trained by gmkim.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("gpt_2_340m_distilled_promptkd_dolly_v1_0_pipeline", lang = "en")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("gpt_2_340m_distilled_promptkd_dolly_v1_0_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: gpt_2_340m_distilled_promptkd_dolly_v1_0_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 848.1 MB

References

https://huggingface.co/gmkim/GPT-2-340M-distilled-PromptKD-Dolly-v1.0

Included Models

  • DocumentAssembler
  • GPT2Transformer