lm-sys / FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Apache License 2.0
35.53k stars 4.36k forks source link

Fine-tuning Vicuna-7B #3396

Open dhruvpes opened 2 weeks ago

dhruvpes commented 2 weeks ago

I am able to run the Vicuna 7B model just fine normally, by providing it with either "messages" (Q&A format) or the "prompt" (Sentence completion capability).

However when I follow the Fine-tuning steps, the first command being pip3 install -e ".[train]" , at some point of running this I get the below error:

image

I have tried n number of different ways to bypass/solve this, only to be futile. Can someone pls help out here?