11 Commits

Author	SHA1	Message	Date
wanghanzi	1e04b4469e	Update QformerMoE & DataProcess 1123	2023-12-01 23:17:44 +08:00
Deyao Zhu	0eba23ce3b	update v2 demo	2023-10-13 03:14:35 +03:00
Deyao Zhu	fb8e2c656a	include llama2	2023-08-28 21:26:00 +03:00
Deyao Zhu	40b514bd21	update readme to include the device statement for demo	2023-04-19 20:00:25 +03:00
Deyao Zhu	322ed189e6	add argument to set the demo device	2023-04-19 19:49:05 +03:00
Deyao Zhu	dadc0d7e69	adding length control and change the default hyperparameter of the conversation to avoid OOM in 3090.	2023-04-18 22:04:50 +03:00
Zhwt	92126a0a32	fix wrong paper PDF link	2023-04-18 17:22:28 +08:00
ZhuDeyao	3e03c8327f	Merge pull request #5 from 152334H/int8 ... consumer gpu inference	2023-04-17 15:34:20 +03:00
XiaoqianShen	378508b83b	Update demo.py	2023-04-17 10:35:02 +03:00
152334H	700f05d079	set num_beam default to 1 instead of completely removing it	2023-04-17 14:56:18 +08:00
Deyao Zhu	f1a33af227	first commit	2023-04-17 01:04:16 +03:00