Edit on GitHub
  • John Snow Labs
  • Mar 28, 2025

English gpt2_medium_int4_18k_alpaca_pipeline pipeline GPT2Transformer from MarcelPower

  • en
  • open_source
  • pipeline
  • onnx

Description

Pretrained GPT2Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.gpt2_medium_int4_18k_alpaca_pipeline is a English model originally trained by MarcelPower.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("gpt2_medium_int4_18k_alpaca_pipeline", lang = "en")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("gpt2_medium_int4_18k_alpaca_pipeline", lang = "en")
val annotations = pipeline.transform(df)

Model Information

Model Name: gpt2_medium_int4_18k_alpaca_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: en
Size: 1.3 GB

References

https://huggingface.co/MarcelPower/gpt2-medium-int4-18k-alpaca

Included Models

  • DocumentAssembler
  • GPT2Transformer