18 Commits

Author	SHA1	Message	Date
hiyouga	bdb496644c	allow non-packing pretraining	2024-03-09 22:21:46 +08:00
hiyouga	e8dd38b7fd	fix #2756 , patch #2746	2024-03-09 02:01:26 +08:00
hiyouga	638234ceee	format style	2024-01-20 20:15:56 +08:00
hiyouga	d9f1cae351	support function calling	2024-01-18 09:54:23 +08:00
hiyouga	4571068e1e	fix #1789	2024-01-09 18:31:27 +08:00
hiyouga	5431be42f9	fix ppo trainer	2023-12-28 18:09:28 +08:00
hiyouga	870426ff70	fix #1742	2023-12-16 20:50:45 +08:00
hiyouga	d3dccd0693	fix ppo trainer save logic	2023-12-04 19:00:19 +08:00
hiyouga	8b681ee273	fix bug	2023-12-03 21:40:40 +08:00
hiyouga	747db40172	ppo support rm server	2023-12-03 21:38:51 +08:00
hiyouga	327d7f7efe	fix #1597	2023-11-30 21:47:06 +08:00
hiyouga	1585962eb7	fix #1668	2023-11-30 21:02:00 +08:00
hiyouga	77d1b14fc2	fix #1658	2023-11-28 20:57:24 +08:00
hiyouga	5021062493	update ppo trainer	2023-11-20 21:39:15 +08:00
hiyouga	99a3f06377	fix #1567	2023-11-20 18:46:36 +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	4736344eb1	disentangle model from tuner and rename modules	2023-11-15 16:29:09 +08:00