search

deep-diver / llamaduo

This project showcases an LLMOps pipeline that fine-tunes a small-size LLM model to prepare for the outage of the service LLM.
https://huggingface.co/papers/2408.13467
Apache License 2.0
286 stars 29 forks source link

Cli/batch inference #14

Closed deep-diver closed 6 months ago

deep-diver commented 6 months ago

first attempt to make separate CLI for each step. This PR focuses on the batch inference. After iterating this, we can apply the same thing for other steps.

deep-diver commented 6 months ago

changes are made to address your comments

deep-diver commented 6 months ago

@sayakpaul

now, record sha instead of branch name! i.e. https://huggingface.co/datasets/chansung/lm_response_test