THUDM
/

chatglm2-6b-32k

Inference Endpoints

Model card Files Files and versions Community

chatglm2-6b-32k / modeling_chatglm.py

Commit History

Add support for Ascend NPU

055c8bd

statelesshz commited on Sep 22, 2023

Optimize the storage of KV cache

1ed39ad

davidlvxin commited on Aug 3, 2023

Init commit

7593daf

davidlvxin commited on Jul 30, 2023