lm-sys/FastChat

support for 4bit quantization from transfomer library.

Open

#1,798 opened on 2023年6月27日

GitHub で見る
 (7 comments) (2 reactions) (0 assignees)Python (38,959 stars) (4,736 forks)batch import
enhancementgood first issue

説明

Loading a vicuna13B using 4bit quantization from the transformers library is possible load_in_4bit. How difficult could be for Fastach to support it?

コントリビューターガイド