lm-sys/FastChat

support for 4bit quantization from transfomer library.

Open

#1.798 geöffnet am 27. Juni 2023

Auf GitHub ansehen
 (7 Kommentare) (2 Reaktionen) (0 zugewiesene Personen)Python (38.959 Stars) (4.736 Forks)batch import
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?

Contributor Guide