lm-sys/FastChat

support for 4bit quantization from transfomer library.

開放

#1,798 建立於 2023年6月27日

 (7 則留言) (2 個反應) (0 位負責人)Python (4,736 個分叉)batch import
enhancementgood first issue

倉庫指標

星標
 (38,959 顆星)
PR 合併指標
 (PR 指標待抓取)

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?

貢獻者指南