github/GLM-130B

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

Autor	SHA1 Mensaxe	Data
Sengxian	28e449b79f Update quantization docs and scripts	%!s(int64=3) %!d(string=hai) anos
Sengxian	96eac9f33b Add 4-bit quantization and CUDA kernels	%!s(int64=3) %!d(string=hai) anos
Sengxian	e10b098020 Add 8-bit quantization	%!s(int64=3) %!d(string=hai) anos