160 Commits

Author SHA1 Message Date
Uminosachi
9e15eca1c1 Set scheduler_specific_kwargs to get_scheduler
Former-commit-id: f04e70dfab44480ef4c015c06470443237f69ba9
2024-05-31 13:45:39 +09:00
hiyouga
3e80365646 10x generate in ppo w/ zero3
https://github.com/huggingface/trl/pull/1483

Former-commit-id: 5dc43ba8b373d8803bc22d88b3d0d95ef8b9c7f8
2024-05-29 00:23:23 +08:00
hiyouga
0de2ab5d16 update dpo, kto trainer
Former-commit-id: 4a6cc3c7046f8b27d05ea53ef216bab6fa7ebfaf
2024-05-29 00:14:29 +08:00
hiyouga
e15389be7d clean kto trainer
Former-commit-id: 76402bd78cbd3a99a544f0ac019468b569b0e1d1
2024-05-28 21:43:26 +08:00
hiyouga
ed2601a909 support SimPO #3900
Former-commit-id: 6b954ce60155cf8334150b795cfc4bb63ca74c8b
2024-05-26 23:46:33 +08:00
hiyouga
664cba05e3 refactor data preprocessing, fix mllm rlhf
Former-commit-id: 53ff2dd24f9121ea30c95063bb72e49a9b31e980
2024-05-24 04:08:25 +08:00
hiyouga
b5a49ad569 improve data process logger
Former-commit-id: 33d0b012b56dbafc9fff87b821c2d1bf1409dbb5
2024-05-18 22:02:42 +08:00
hiyouga
d24969bb7e improve KTO impl., replace datasets
Former-commit-id: e56a57ddcf061de6e4acc8679f7dbf0b68364986
2024-05-18 03:44:56 +08:00
enji.zhou
d16a1d9ed0 add kto
Former-commit-id: ec51986cf70b0bdd79b8141e45916670fb97a08e
2024-05-17 13:09:17 +08:00
hiyouga
ee759aa0d8 rename package
Former-commit-id: a07ff0c083558cfe6f474d13027642d3052fee08
2024-05-16 18:39:08 +08:00