Edit on GitHub
  • John Snow Labs
  • Dec 19, 2024

Turkish gpt2_turkish_128_token_pipeline pipeline GPT2Transformer from cenkersisman

  • tr
  • open_source
  • pipeline
  • onnx

Description

Pretrained GPT2Transformer, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.gpt2_turkish_128_token_pipeline is a Turkish model originally trained by cenkersisman.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("gpt2_turkish_128_token_pipeline", lang = "tr")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("gpt2_turkish_128_token_pipeline", lang = "tr")
val annotations = pipeline.transform(df)

Model Information

Model Name: gpt2_turkish_128_token_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: tr
Size: 467.1 MB

References

https://huggingface.co/cenkersisman/gpt2-turkish-128-token

Included Models

  • DocumentAssembler
  • GPT2Transformer