Commit Graph

31 Commits

Author SHA1 Message Date
hiyouga
c187b20aaa use robust envs 2024-05-14 21:36:42 +08:00
hiyouga
4777efe517 fix #3658 2024-05-12 01:25:16 +08:00
hiyouga
ed8f8be752 update api and support abort eval in webui 2024-05-04 15:59:15 +08:00
hiyouga
24cc93ab15 fix eval in webui 2024-05-04 00:19:19 +08:00
hiyouga
9585838ebe fix callback log multigpu #3559 2024-05-03 21:24:27 +08:00
hiyouga
245fe47ece update webui and add CLIs 2024-05-03 02:58:23 +08:00
hiyouga
17bf8a2c3a support ORPO 2024-03-31 18:29:50 +08:00
hiyouga
b19c14870d fix #3010 2024-03-28 18:31:17 +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
898ec3696a fix #2161 2024-01-11 17:04:13 +08:00
hiyouga
4571068e1e fix #1789 2024-01-09 18:31:27 +08:00
hiyouga
368b31f6b7 fix #2067 2024-01-04 22:53:03 +08:00
hiyouga
bf6f6aeefe fix #1696 2023-12-01 15:34:50 +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
273745f9b9 fix eval resuming in webui 2023-10-15 15:45:38 +08:00
hiyouga
3ad8c92eca tiny fix 2023-10-15 05:02:48 +08:00
hiyouga
1e9401744c fix callback 2023-10-15 04:59:44 +08:00
hiyouga
accde3cd39 implement webui resuming training 2023-10-15 04:52:19 +08:00
hiyouga
d4be857e23 fix #762 #814 2023-09-12 16:10:10 +08:00
hiyouga
0fbece85a7 update flashattn, fix ppo save model 2023-09-11 17:25:36 +08:00
hiyouga
b218c271ed remove PeftTrainer 2023-09-10 22:23:23 +08:00
hiyouga
3ec4351cfd support DPO training (2305.18290) 2023-08-11 03:02:53 +08:00
hiyouga
08f180e788 modify code structure 2023-08-02 23:17:36 +08:00
hiyouga
0411a4b3e1 support streaming data, fix #284 #274 #268 2023-07-31 23:33:00 +08:00
hiyouga
cadeac0f44 fix #176 2023-07-18 16:36:24 +08:00
hiyouga
552d773dad fix callback 2023-07-15 22:01:43 +08:00
hiyouga
d640c5545f Update callbacks.py 2023-07-15 17:39:16 +08:00
hiyouga
22d9a9c2af fix callback 2023-07-15 17:18:16 +08:00
hiyouga
f751376613 modity code structure 2023-07-15 16:54:28 +08:00