github/GLM-130B

miroir de https://github.com/THUDM/GLM-130B.git

Auteur	SHA1 Message	Date
Sengxian	c64d6ea33c Fix quantization argument bug	il y a 3 ans
Sengxian	96eac9f33b Add 4-bit quantization and CUDA kernels	il y a 3 ans
Sengxian	e10b098020 Add 8-bit quantization	il y a 3 ans