End-to-End-LLM icon indicating copy to clipboard operation
End-to-End-LLM copied to clipboard

Published 20 hours ago • verified publisher icon openhackathons-org

Feature Request: Fine-tune Llama-2-7B with Custom Dataset

Open programmah opened this issue 1 year ago • 0 comments

This feature request is required as part of an End-to-End pipeline. The process should include:

  • dataset preprocessing
  • use of PEFT method to fine-tune llama-2-7b for text generation task
  • Fine-tuned and based model merging
  • inferencing

programmah avatar Feb 06 '24 08:02 programmah