Commit Graph

30 Commits

Author SHA1 Message Date
hiyouga
8717e98200 fix #2777 #2895
Former-commit-id: 9bec3c98a2
2024-03-20 17:59:45 +08:00
hiyouga
4a4e4b4354 support layerwise galore
Former-commit-id: 8664262cde
2024-03-10 00:24:11 +08:00
hiyouga
868444e124 allow non-packing pretraining
Former-commit-id: bdb496644c
2024-03-09 22:21:46 +08:00
hiyouga
c561b268ef fix #2756 , patch #2746
Former-commit-id: e8dd38b7fd
2024-03-09 02:01:26 +08:00
hiyouga
2c010c72b8 support galore
Former-commit-id: 28f7862188
2024-03-07 22:41:36 +08:00
hiyouga
d1e6e02461 fix #2649
Former-commit-id: 4e5fae2fac
2024-03-01 13:02:41 +08:00
stephen
1b4d54b873 update project_kwargs for ppo config
Former-commit-id: 42c23798f2
2024-02-21 13:47:38 +08:00
hiyouga
7cc0721028 fix #2189
Former-commit-id: b988ce0a0c
2024-02-04 00:47:37 +08:00
hiyouga
b27e91222c format style
Former-commit-id: 638234ceee
2024-01-20 20:15:56 +08:00
hiyouga
2f7684a8ee fix tests
Former-commit-id: f6d6e00337
2024-01-20 19:58:04 +08:00
hiyouga
4e3bfb799d support function calling
Former-commit-id: d9f1cae351
2024-01-18 09:54:23 +08:00
hiyouga
6378864390 fix #2161
Former-commit-id: 898ec3696a
2024-01-11 17:04:13 +08:00
hiyouga
61960189b2 fix #1789
Former-commit-id: 4571068e1e
2024-01-09 18:31:27 +08:00
hiyouga
d0946f08db fix ppo trainer
Former-commit-id: 5431be42f9
2023-12-28 18:09:28 +08:00
hiyouga
8154b4bdf6 fix #1742
Former-commit-id: 870426ff70
2023-12-16 20:50:45 +08:00
hiyouga
027caabbb6 fix ppo trainer save logic
Former-commit-id: d3dccd0693
2023-12-04 19:00:19 +08:00
hiyouga
6493558c3b fix bug
Former-commit-id: 8b681ee273
2023-12-03 21:40:40 +08:00
hiyouga
64eead3fb1 ppo support rm server
Former-commit-id: 747db40172
2023-12-03 21:38:51 +08:00
hiyouga
1cb390b9b2 implement rm server #1543
Former-commit-id: 7df4f3ab20
2023-12-03 20:52:54 +08:00
hiyouga
3d291a82d3 fix #1597
Former-commit-id: 327d7f7efe
2023-11-30 21:47:06 +08:00
hiyouga
ba6d290d0b fix #1668
Former-commit-id: 1585962eb7
2023-11-30 21:02:00 +08:00
hiyouga
ecfc7d1b50 fix #1658
Former-commit-id: 77d1b14fc2
2023-11-28 20:57:24 +08:00
hiyouga
f06c4c8f7a update ppo trainer
Former-commit-id: 5021062493
2023-11-20 21:39:15 +08:00
hoshi-hiyouga
d72f123851 Merge pull request #1553 from hannlp/hans
Change the default argument settings for PPO training

Former-commit-id: 48211e3799
2023-11-20 20:32:55 +08:00
hiyouga
682d81caa9 fix #1567
Former-commit-id: 99a3f06377
2023-11-20 18:46:36 +08:00
Yuchen Han
a419122179 Update workflow.py
Former-commit-id: eeb5249d0b
2023-11-17 00:16:27 -08:00
hiyouga
678052a7ef fix rlhf callback
Former-commit-id: 1817ffc86f
2023-11-16 03:26:19 +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
06a4820836 disentangle model from tuner and rename modules
Former-commit-id: 4736344eb1
2023-11-15 16:29:09 +08:00