lm-sys/FastChat

support for 4bit quantization from transfomer library.

开放

#1,798 创建于 2023年6月27日

 (7 条评论) (2 个反应) (0 位负责人)Python (4,736 个派生)batch import
enhancementgood first issue

仓库指标

星标
 (38,959 个星标)
PR 合并指标
 (PR 指标待抓取)

描述

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

贡献者指南