THUDM
/

chatglm2-6b-int4

Inference Endpoints

Model card Files Files and versions Community

chatglm2-6b-int4 / quantization.py

Commit History

Update quantized gemm kernel

5579a9f

duzx16 commited on Jul 16, 2023

Add cpu kernel

8b97bf2

duzx16 commited on Jun 26, 2023

Init commit

8668ecb

duzx16 commited on Jun 25, 2023