21 Commits

Author SHA1 Message Date
hiyouga
caf4fa46e0 patch modelscope
Former-commit-id: 8888cf53f040f5a2d8c0e59cddf79b252449bf58
2023-12-01 22:53:15 +08:00
yuze.zyz
2ea08c6631 support ms
Former-commit-id: fdd4f94f563110ef9f96ab4a7fd954def32e9785
2023-11-29 20:36:55 +08:00
hiyouga
685d0c975a support full-parameter PPO
Former-commit-id: 4af967d69475e1c9fdf1a7983cd6b83bd431abff
2023-11-16 02:08:04 +08:00
hiyouga
dc69e3025e add todo
Former-commit-id: 0bd884feb11736d0ab24ca19885151cb47d9dcd3
2023-11-10 14:38:18 +08:00
hiyouga
a3973795a0 fix ppo train and dpo eval
Former-commit-id: ced863031836632cb5920e22ae6991f251372118
2023-11-07 22:48:51 +08:00
hiyouga
08df3dca98 upgrade peft, fix #1088 #1411
Former-commit-id: aa7d104f8e050d12cb8f585bc8a52c850995500f
2023-11-07 16:13:36 +08:00
hiyouga
31969e78f7 reimplement neftune
Former-commit-id: efe9e5a194d3a9f052701d904715238816e4c09e
2023-10-22 16:15:08 +08:00
hiyouga
cb68572bce refactor export, fix #1190
Former-commit-id: 30e60e37023a7c4a2db033ffec0542efa3d5cdfb
2023-10-15 16:01:48 +08:00
hiyouga
7fea444d48 fix #1184
Former-commit-id: 5b069a967823e659dbc70b0d50361b3ad248087e
2023-10-14 19:20:11 +08:00
hiyouga
f1a8fcf917 refactor model_dtype, fix PPO trainer
Former-commit-id: 3e17ee5afbcb823a7c9a2f91864b3750cd79edb4
2023-10-11 23:16:01 +08:00
hiyouga
4617413bde fix layer norm dtype
Former-commit-id: 67af21961b68d9b54d07b09e444c7140869f26da
2023-09-28 00:25:55 +08:00
hiyouga
d6f5a3cae9 support LongLoRA
Former-commit-id: 0832ed37e7947d699f17375648a52f80752c2b6b
2023-09-27 21:55:50 +08:00
hiyouga
d8ab75ee44 fix #944
Former-commit-id: 032245647848aaa4167086636b6c985268c5fee3
2023-09-21 19:51:02 +08:00
hiyouga
f326178f89 support FlashAttention2
Former-commit-id: 23e56c5554b948d4f08ad87849b261eafd2c7890
2023-09-10 20:43:56 +08:00
hiyouga
801d1fa7b9 change to right-padding, update reward score #803
Former-commit-id: baa90415bc8f5ebd423d001378b51c3a3a6c2ec7
2023-09-08 20:04:31 +08:00
hiyouga
c5fcf5b3a5 refactor dataset_attr, add eos in pt, fix #757
Former-commit-id: 0feec9a830b917b36686b61938a66e842eccf930
2023-09-01 19:00:45 +08:00
hiyouga
a15a602809 support rope scaling, fix #475 #476 #478
Former-commit-id: 337d5f68b72230e545e7a94ca789187c7a2b7187
2023-08-12 20:46:27 +08:00
hiyouga
98aa629843 Release v0.1.6
Former-commit-id: 43c8b3c3c8bfb2e32d17fb3e8b194938e37d54bd
2023-08-11 23:25:57 +08:00
hiyouga
7ada4f5f6f support DPO training (2305.18290)
Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f
2023-08-11 03:02:53 +08:00
jiongxuc
326f8c71a3 huggingface login for projects must login while running
Former-commit-id: 0a4a2a1d3e0ff1f57215512d294d782080bd383c
2023-08-10 14:57:12 +08:00
hiyouga
a69b1b1c3a modity code structure
Former-commit-id: 0682ed357210897e0b67c4a6eb31a94b3eb929f1
2023-07-15 16:54:28 +08:00