ChatGLM2-6B

Author	SHA1	Message	Date
Qin Jianxiang	f1f7e4bbf8	Merge branch 'main' into main	2023-06-26 17:30:44 +08:00
duzx16	1c144d168b	Update streamlit web demo	2023-06-26 17:07:24 +08:00
duzx16	385040e6c7	Fix prompt in cli demo	2023-06-26 16:49:56 +08:00
duzx16	9d439304d4	Remove device="cuda"	2023-06-26 14:03:37 +08:00
duzx16	b35782c46e	Add gcc installation	2023-06-26 13:52:12 +08:00
duzx16	d3c58147ed	Update requirements.txt	2023-06-26 13:34:04 +08:00
duzx16	3ee8ff7717	Delete device='cuda'	2023-06-26 13:32:14 +08:00
Qin Jianxiang	a3ba2275ed	small change of comment about multiple GPUs support	2023-06-26 10:37:38 +08:00
Qin Jianxiang	08ffab941f	Multiple GPUs support: migrate the code from ChatGLM-6B, make a few modifications to support ChatGLM2.	2023-06-26 10:29:19 +08:00
Qin Jianxiang	55d7548e4c	typo fixed: ChatGLM -> ChatGLM2	2023-06-26 10:17:03 +08:00
duzx16	07957bacf8	Add int model	2023-06-25 21:01:01 +08:00
duzx16	6fed3d4dc2	Remove bfloat16 in web demo	2023-06-25 17:35:08 +08:00
duzx16	c410768fae	Update README	2023-06-25 16:27:44 +08:00
duzx16	57d6d4d346	Add wechat image	2023-06-25 16:24:46 +08:00
duzx16	aec54b3f07	init commit	2023-06-25 15:32:49 +08:00