Commit Graph

106 Commits

Author SHA1 Message Date
BUAADreamer
641c97ba74 add llava and instructblip
Former-commit-id: 142fb6f4541a1acfefe66ff2574dabde53b00c06
2024-04-25 00:22:43 +08:00
BUAADreamer
20e05970ab add multimodal LLM BLIP-2 and InstructBLIP
Former-commit-id: a730f89a972f1a9d37c718c716f199cb8d4903b2
2024-04-23 18:45:43 +08:00
hiyouga
82bbad8477 fix optimizers
Former-commit-id: f811eee2fa12a89a55a9c5d3a05a1521b4347727
2024-04-21 20:40:54 +08:00
hiyouga
b353a080cb fix bug in galore optimizer
Former-commit-id: c05ac23261a5a8ba893c2918a43dc7777307407b
2024-04-21 18:53:22 +08:00
hiyouga
d41793228e support badam for all stages
Former-commit-id: 7a1380646119bfe6855f73dd90570defcea05281
2024-04-16 17:44:48 +08:00
hoshi-hiyouga
71743d4726 Update utils.py
Former-commit-id: 01147536b2bb507e87e033fa696e9eb39fe96bbe
2024-04-16 17:30:12 +08:00
hoshi-hiyouga
3f1f729d88 Update trainer.py
Former-commit-id: c6163be1444c00dd000f288e2f834968bd932981
2024-04-16 17:29:52 +08:00
Jonery
2ba03e6ef3 resolve gradient checkpointing issue.
Former-commit-id: 6df9135d063bb6102f0cbcdf0d702076f5febbae
2024-04-16 12:05:27 +08:00
Jonery
22188f1fa3 Feature BAdam
Former-commit-id: d8d2807fbcf587c37f7fd34a23e9397d2775ceed
2024-04-15 23:15:27 +08:00
hiyouga
be206df674 update examples
Former-commit-id: 369294b31c8a03a1cafcee83eb31a817007d3c49
2024-04-15 22:14:34 +08:00
hiyouga
64da8145bf fix model card
Former-commit-id: 920e7149bf2b559c9829aa4b11cfb6d00bbb2f9e
2024-04-12 17:11:59 +08:00
hiyouga
4cb8cc563d fix #3238
Former-commit-id: 4d7e81ab4722d13bec6ca1af141f94bdc74d0883
2024-04-12 14:28:11 +08:00
hiyouga
d97150c571 fix resize vocab at inference #3022
Former-commit-id: c243720b89eec0af2872fa3c7980a0026d893f4d
2024-04-03 18:14:24 +08:00
hiyouga
99ed1657db fix #3116
Former-commit-id: b7256aa33d761280751518c20f29f9b8ea3fb025
2024-04-03 14:47:59 +08:00
hiyouga
75819c1220 simplify readme
Former-commit-id: 0da6ec2d516326fe9c7583ba71cd1778eb838178
2024-04-02 20:07:43 +08:00
hiyouga
357a32d7a0 fix #3083
Former-commit-id: ff9a3f73961a362d0ddc22079f80a85465fffda8
2024-04-01 22:53:52 +08:00
hiyouga
0116675349 fix ORPO loss
Former-commit-id: 5544ddde9087f00f9e20b78d0079f20c2f5d1604
2024-04-01 14:42:41 +08:00
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
899e9e091c use log1p in orpo loss
https://github.com/huggingface/trl/pull/1491

Former-commit-id: 3b15d495264b00a4f8716bafea334778874963d7
2024-03-31 19:27:08 +08:00
hiyouga
e6c7e6e667 support ORPO
Former-commit-id: f44a4c27e2461cdaa1b16865f597a31033c0e6d9
2024-03-31 18:29:50 +08:00
marko1616
fb6e653443 Fix Llama model save for full param train
Former-commit-id: ca17b5db4f97c3ec9fe2004877f150e8f51ab4b5
2024-03-30 23:45:04 +08:00
hiyouga
cc249506a8 release v0.6.1
Former-commit-id: a59d823f554505b2e649e6e111b9dee8306d3ad8
2024-03-29 11:36:08 +08:00
hiyouga
5c8794ad1a fix #2982
Former-commit-id: e5e6a0c50c7a1c0052ed6b459450b9735ff2c9a1
2024-03-28 20:22:31 +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
f62e99a71d release v0.6.0 (real)
Former-commit-id: 34e06bf408ccd21e674f896703f1c7b62e97e1ca
2024-03-25 23:37:48 +08:00
hiyouga
80861ca109 release v0.6.0
Former-commit-id: 51910d5803eb718e4976da0b3bfcdc5eeeea48eb
2024-03-25 22:38:56 +08:00
hiyouga
046bd94ce4 tiny fix
Former-commit-id: c39cf3439a3025f703d50ac414c10ef3c8486a1f
2024-03-25 21:18:08 +08:00
marko1616
e1493e0192 pass ruff check
Former-commit-id: 8534b069a05121eb041371a6becccf0a1a23f268
2024-03-24 16:12:10 +08:00
marko1616
e21a822744 fix Llama lora merge crash
Former-commit-id: 46f7d8e6b85f73fb0c51c8b08bd9955c3b171d93
2024-03-24 03:06:11 +08:00
marko1616
1a6f961ab1 fix Llama lora merge crash
Former-commit-id: a8bd8e9149ff79a2707fec9c6d006761cfdd0dee
2024-03-24 02:55:23 +08:00
marko1616
7a5c2f4766 fix Llama lora merge crash
Former-commit-id: c29a2893f58cf7a916ff05b2725fadf1ad2c4c9a
2024-03-24 02:44:35 +08:00
hiyouga
2d12e88c23 fix #2777 #2895
Former-commit-id: 54d5f62d29456a8d9d0c0dd3d0bbfffe48935803
2024-03-20 17:59:45 +08:00
hiyouga
2f8eb620f6 fix packages
Former-commit-id: 2f9f334a123d43267bfb3dd26aaa1ad285ffe7a5
2024-03-17 22:32:03 +08:00
hiyouga
d3b7e4e433 fix export
Former-commit-id: 4e996f194406d7eb27b2bde290a12c82c41219d0
2024-03-15 15:06:30 +08:00
hiyouga
b83aedd040 tiny fix
Former-commit-id: bf8123669be334338b4268d0a8f7703ff2cf6255
2024-03-14 21:19:06 +08:00
hiyouga
0d245f67ea fix export
Former-commit-id: c9b968b84c97c9a00fbb43194c3adc9354d74f3b
2024-03-14 18:17:01 +08:00
hiyouga
e49a9aa457 fix bug
Former-commit-id: 38c618b797ec219c2c45de960c9cbe50ec524c94
2024-03-13 23:55:31 +08:00
hiyouga
36bf98aea8 fix bug
Former-commit-id: 47ee0276830adbed65bc111d5a83049e77ad360a
2024-03-13 23:43:42 +08:00
hiyouga
4ef67ed4dd improve lora+ impl.
Former-commit-id: 332bad25455a70ad9204e7dd384bb086d789aa39
2024-03-13 23:32:51 +08:00
齐保元
3c15d4cbec [FEATURE]: ADD LORA+ ALGORITHM
Former-commit-id: c35b3c3b1e27171f8a703f88ede1dc8a84c80a56
2024-03-13 19:43:27 +08:00
hiyouga
a45bc9a96b fix #2775
Former-commit-id: a5c7feb3e8089f4deff760b00a9f84425957c419
2024-03-11 00:42:54 +08:00
hiyouga
0aacc41252 support layerwise galore
Former-commit-id: d43a4da0947897d0be3f62fad3107754d4c89f2b
2024-03-10 00:24:11 +08:00
hiyouga
56565bdbd4 allow non-packing pretraining
Former-commit-id: 3fee5cc5a3db9ce874ad90f2500ec092d904bd4e
2024-03-09 22:21:46 +08:00
hiyouga
aa48a7d9b2 fix #2766
Former-commit-id: a8cd556230c1d0bc4e090acc2276c035910ce6f6
2024-03-09 21:35:24 +08:00
hiyouga
e16912b0c0 fix #2756 , patch #2746
Former-commit-id: 627d1c91e675f1d9ebf47bad123cbbf29821da4d
2024-03-09 02:01:26 +08:00
hiyouga
b5187e4104 fix galore
Former-commit-id: 62a3ceeef8f60caef43ccc7f971a0c9184e21296
2024-03-08 00:44:51 +08:00
hiyouga
3f56782ffa support galore
Former-commit-id: b67a4a46a88d83bb2a3459b3317b66cda15e0171
2024-03-07 22:41:36 +08:00