250 Commits

Author	SHA1	Message	Date
hiyouga	3552035d7e	add model urls	2023-12-13 00:09:17 +08:00
hiyouga	96380f5e18	support mixtral	2023-12-12 11:39:04 +08:00
hiyouga	e25f7bae16	add models	2023-12-06 13:33:18 +08:00
hiyouga	c9b166615c	fix #1715	2023-12-03 22:35:47 +08:00
hiyouga	747db40172	ppo support rm server	2023-12-03 21:38:51 +08:00
hiyouga	03d05991f8	fix #1707 #1710	2023-12-03 11:33:12 +08:00
hiyouga	6e7af11b98	add xuanyuan models	2023-12-02 00:35:29 +08:00
hiyouga	f57445c7a0	fix gptq training	2023-12-02 00:27:15 +08:00
hiyouga	662d9a3a4e	fix #1703	2023-12-01 22:55:41 +08:00
hiyouga	bd42c229b0	patch modelscope	2023-12-01 22:53:15 +08:00
hoshi-hiyouga	00f5c9ee16	Merge branch 'main' into feat/support_ms	2023-12-01 20:23:46 +08:00
yuze.zyz	5a2392f105	remove useless code	2023-12-01 17:28:23 +08:00
tastelikefeet	d9e52957e2	fix bug	2023-12-01 17:27:00 +08:00
yuze.zyz	5aa6751e52	add readme	2023-12-01 16:11:30 +08:00
hiyouga	e597d3c084	tiny fix	2023-12-01 15:58:50 +08:00
hoshi-hiyouga	d043a4e7ba	Merge pull request #1690 from billvsme/main ... Improve get_current_device	2023-12-01 15:44:35 +08:00
hiyouga	bf6f6aeefe	fix #1696	2023-12-01 15:34:50 +08:00
tastelikefeet	8ce4d11e38	add model	2023-12-01 15:06:17 +08:00
billvsme	40dfcbc3d4	improve get_current_device	2023-11-30 22:40:35 +08:00
hiyouga	509abe8864	add models	2023-11-30 19:16:13 +08:00
yuze.zyz	fb2204c183	fix	2023-11-29 21:43:58 +08:00
yuze.zyz	d38a2e7341	support ms	2023-11-29 20:36:55 +08:00
hiyouga	475a3fa0f4	fix #1659	2023-11-28 20:52:28 +08:00
hiyouga	ff1c289229	support Yi-34B-Chat models	2023-11-23 19:31:49 +08:00
hiyouga	5021062493	update ppo trainer	2023-11-20 21:39:15 +08:00
hiyouga	1740131d63	fix #1558	2023-11-19 14:15:47 +08:00
hiyouga	999bc0ed93	fix packages	2023-11-17 16:11:48 +08:00
Shaowen Wang	397e948984	Fix: Change rouge-chinese package name to rouge_chinese ... To reproduce: python: importlib.util.find_spec('rouge-chinese') -> None importlib.util.find_spec('rouge_chinese') -> ModuleSpec(name='rouge_chinese'...) from rouge_chinese import Rouge print(Rouge.__module__) -> rouge_chinese	2023-11-16 20:12:35 -06:00
hiyouga	6efa38be46	fix bug in web ui	2023-11-16 15:21:24 +08:00
hiyouga	7537dd434f	update ppo and demo in webui	2023-11-16 14:55:26 +08:00
hiyouga	83cee2a604	tiny fix	2023-11-16 03:27:19 +08:00
hiyouga	1817ffc86f	fix rlhf callback	2023-11-16 03:26:19 +08:00
hiyouga	ce78303600	support full-parameter PPO	2023-11-16 02:08:04 +08:00
hiyouga	1e19cf242a	update readme and constants	2023-11-15 18:04:37 +08:00
hiyouga	4736344eb1	disentangle model from tuner and rename modules	2023-11-15 16:29:09 +08:00
hiyouga	35cc1e28f6	release v0.2.2, fix #1478 #1466	2023-11-13 23:09:05 +08:00
hiyouga	442aefb925	refactor evaluation, upgrade trl to 074	2023-11-13 22:20:35 +08:00
hiyouga	4bd8e3906d	fix flashattn warning	2023-11-10 18:34:54 +08:00
hiyouga	3697a3dc9a	refactor constants	2023-11-10 14:16:10 +08:00
hiyouga	386f590209	add template, modify datasets	2023-11-09 15:53:23 +08:00
hiyouga	479d0af2dc	delete file	2023-11-07 16:20:12 +08:00
hiyouga	b2a60905f3	upgrade peft, fix #1088 #1411	2023-11-07 16:13:36 +08:00
hiyouga	a7eeb8e17c	update templates	2023-11-06 12:25:47 +08:00
hiyouga	d08f5e8a14	fix deepseek template	2023-11-05 13:08:46 +08:00
hiyouga	2a8a258195	support deepseek coder #1378	2023-11-05 12:51:03 +08:00
hiyouga	f4e4a04529	fix #1316	2023-10-31 11:32:08 +08:00
hiyouga	f28a034a9b	update constants	2023-10-29 13:30:20 +08:00
hiyouga	52fc24d166	fix vicuna template	2023-10-27 22:15:25 +08:00
hiyouga	4117f38827	fix chatglm3 template	2023-10-27 21:12:06 +08:00
hiyouga	1c0ab9a908	support chatglm3	2023-10-27 19:16:28 +08:00