30 Commits

Author	SHA1	Message	Date
hiyouga	89cf856776	fix #1771 and temporarily fix #1764 ... Former-commit-id: d42c0b1d34	2023-12-08 16:26:20 +08:00
hiyouga	cd2b0a024b	fix #1715 ... Former-commit-id: c9b166615c	2023-12-03 22:35:47 +08:00
hiyouga	1cb390b9b2	implement rm server #1543 ... Former-commit-id: 7df4f3ab20	2023-12-03 20:52:54 +08:00
hiyouga	2279b1948e	fix #1707 #1710 ... Former-commit-id: 03d05991f8	2023-12-03 11:33:12 +08:00
hiyouga	6720189f3f	fix #1642 ... Former-commit-id: b69763ff92	2023-12-02 00:37:53 +08:00
hiyouga	4cc08e00c7	fix gptq training ... Former-commit-id: f57445c7a0	2023-12-02 00:27:15 +08:00
hiyouga	c8eff09c7c	tiny fix ... Former-commit-id: a973ce6e89	2023-12-01 23:37:10 +08:00
hiyouga	e0da912f8e	fix gptq model inference ... Former-commit-id: 01e6c539b0	2023-12-01 23:34:14 +08:00
hiyouga	c60e79c12e	patch modelscope ... Former-commit-id: bd42c229b0	2023-12-01 22:53:15 +08:00
yuze.zyz	b2200409f5	add readme ... Former-commit-id: 5aa6751e52	2023-12-01 16:11:30 +08:00
yuze.zyz	45925e4a9c	fix ... Former-commit-id: fb2204c183	2023-11-29 21:43:58 +08:00
yuze.zyz	e08e0e5814	support ms ... Former-commit-id: d38a2e7341	2023-11-29 20:36:55 +08:00
hiyouga	ae1048db6d	fix #1659 ... Former-commit-id: 475a3fa0f4	2023-11-28 20:52:28 +08:00
hiyouga	4966bd7911	support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569 ... Former-commit-id: 9ea9380145	2023-11-20 22:52:11 +08:00
hiyouga	f06c4c8f7a	update ppo trainer ... Former-commit-id: 5021062493	2023-11-20 21:39:15 +08:00
hiyouga	a7b1632ace	fix value head model resuming ... Former-commit-id: 2a36fd5064	2023-11-20 19:01:37 +08:00
hiyouga	682d81caa9	fix #1567 ... Former-commit-id: 99a3f06377	2023-11-20 18:46:36 +08:00
hiyouga	d1e03512f4	fix model card network issue ... Former-commit-id: 211b2db5a8	2023-11-19 23:03:19 +08:00
hiyouga	48d6d925f7	fix #1558 ... Former-commit-id: 1740131d63	2023-11-19 14:15:47 +08:00
hiyouga	112108d564	fix evaluator and cached_file in 4.31.0 ... Former-commit-id: ff6056405d	2023-11-18 19:39:23 +08:00
hiyouga	0d98d1a28c	fix quantization ... Former-commit-id: ccb0f58e22	2023-11-17 22:21:29 +08:00
hiyouga	f9df6c17ed	fix #1550 ... Former-commit-id: 1bbc1be95e	2023-11-17 17:23:13 +08:00
hiyouga	3f53155a90	fix bug in web ui ... Former-commit-id: 6efa38be46	2023-11-16 15:21:24 +08:00
hiyouga	0ed0b8f9c5	fix bug in freeze tuning ... Former-commit-id: ff52b1779c	2023-11-16 14:25:11 +08:00
hiyouga	678052a7ef	fix rlhf callback ... Former-commit-id: 1817ffc86f	2023-11-16 03:26:19 +08:00
hiyouga	b71da932eb	fix bug in PPO training ... Former-commit-id: 856522a3df	2023-11-16 02:32:54 +08:00
hiyouga	eb5a852dd5	fix import bug ... Former-commit-id: 35b91ea34c	2023-11-16 02:27:03 +08:00
hiyouga	f441932bd1	support full-parameter PPO ... Former-commit-id: ce78303600	2023-11-16 02:08:04 +08:00
hiyouga	e30290444a	support multiple modules in freeze training #1514 ... Former-commit-id: 4907452d95	2023-11-15 17:08:18 +08:00
hiyouga	06a4820836	disentangle model from tuner and rename modules ... Former-commit-id: 4736344eb1	2023-11-15 16:29:09 +08:00