How to access int8 with 13b version?
Meathelix1 opened this issue · 1 comments
Meathelix1 commented
Hello, I would like to know how we can access the 13b int8 version for the demo?
JetRunner commented
https://github.com/project-baize/baize/blob/ccf0bb8485657b7c16a57456bbb835503bac2456/demo/app.py#L18
Change this line to tokenizer, model, device = load_tokenizer_and_model(base_model, adapter_model, load_8bit=True)