lm-sys/FastChat
Auf GitHub ansehensupport for 4bit quantization from transfomer library.
Open
#1.798 geöffnet am 27. Juni 2023
enhancementgood first issue
Beschreibung
Loading a vicuna13B using 4bit quantization from the transformers library is possible load_in_4bit. How difficult could be for Fastach to support it?