THUDM/chatglm-6b-int4-qe

like0

Upload ChatGLM-6B-INT4-QE

Upload ChatGLM-6B-INT4-QE

Update README.md

Slim embedding

Slim embedding

Drop icetk dependency

Fix attention score on mps

Upload pytorch_model.bin

Slim embedding

Upload ChatGLM-6B-INT4-QE

Fix parallel cpu kernel

Update README.md

Update README.md