18 Commits

Author SHA1 Message Date
hiyouga
bf10e23dc8 fix IPO and ORPO loss
Former-commit-id: fc27955732aedbb12003faf19b760e2768b228f2
2024-04-01 14:37:53 +08:00
hiyouga
f59dd028e5 fix plots
Former-commit-id: 81355671296b84d438967463bb2a92934ff31aae
2024-03-31 19:43:48 +08:00
hiyouga
e6c7e6e667 support ORPO
Former-commit-id: f44a4c27e2461cdaa1b16865f597a31033c0e6d9
2024-03-31 18:29:50 +08:00
hiyouga
27f5c967e4 update trainers
Former-commit-id: d0dd6eefed0b86895ed00a7cafb331e5193db645
2024-03-28 18:16:27 +08:00
hoshi-hiyouga
702ddf0749 fix ds optimizer
Former-commit-id: 2675127070a1e7584e71039a11c1ebac54ddd1db
2024-03-26 23:39:56 +08:00
hiyouga
52eb06e2ee fix #2961
Former-commit-id: 616917bb3be7f71073b56ad8c7bc4e164b08b9b5
2024-03-26 17:26:14 +08:00
hiyouga
2d12e88c23 fix #2777 #2895
Former-commit-id: 54d5f62d29456a8d9d0c0dd3d0bbfffe48935803
2024-03-20 17:59:45 +08:00
hiyouga
56565bdbd4 allow non-packing pretraining
Former-commit-id: 3fee5cc5a3db9ce874ad90f2500ec092d904bd4e
2024-03-09 22:21:46 +08:00
hiyouga
c7875bdf27 fix #2532
Former-commit-id: 23a8e64f1c47cd473c627effbe271233c136369c
2024-02-21 21:55:14 +08:00
hiyouga
c0e4eebf17 format style
Former-commit-id: 53b683531b83cd1d19de97c6565f16c1eca6f5e1
2024-01-20 20:15:56 +08:00
hiyouga
e5a751ded0 support longlora for main branch
Former-commit-id: f869501ad4c368df26534c41f62c6d63c6be17dd
2024-01-20 19:25:22 +08:00
hiyouga
a9fc7dbfa6 support function calling
Former-commit-id: 66533b3f65babf2429c92c0f8fafe4eff5e0ff63
2024-01-18 09:54:23 +08:00
hiyouga
215b4b5c03 fix #2164
Former-commit-id: abe23bb4aca4fa571ebafc329ec9a9d457e37d41
2024-01-12 00:27:57 +08:00
hiyouga
8465803bec fix dpo trainer
Former-commit-id: c160dd7cd86e296e32775ace2e4258a473449c41
2023-12-23 01:51:55 +08:00
hiyouga
9cdaa43d1c support unsloth
Former-commit-id: b857f00234b90b785d82ca7cdb29af3d948b1a7b
2023-12-23 00:14:33 +08:00
hiyouga
3eec0052cc support dpo-ftx
Former-commit-id: 86dfa04f9821556019fa777106787f73eb70b452
2023-12-16 19:21:41 +08:00
hiyouga
685d0c975a support full-parameter PPO
Former-commit-id: 4af967d69475e1c9fdf1a7983cd6b83bd431abff
2023-11-16 02:08:04 +08:00
hiyouga
5a206d54c9 disentangle model from tuner and rename modules
Former-commit-id: 02cbf91e7e424f8379c1fed01b82a5f7a83b6947
2023-11-15 16:29:09 +08:00