105 Commits

Author SHA1 Message Date
hiyouga
c0afc4074f support unsloth generate
Former-commit-id: b1deb0a0b920645884e58f8206b1842c144c1c52
2024-04-24 04:46:53 +08:00
hiyouga
6a3ee1edd9 fix optimizers
Former-commit-id: fbbe0dba2f244557fff8ac0076a9f312d0aa01ab
2024-04-21 20:40:54 +08:00
hiyouga
9e45f82be7 fix bug in galore optimizer
Former-commit-id: 5c62881c5a59cfcc5a76d365263c8ad8c817ce49
2024-04-21 18:53:22 +08:00
hiyouga
0a94fab357 support badam for all stages
Former-commit-id: e3d8fc75eb2cfc54efd35bfd9ad6c4ac5acc458c
2024-04-16 17:44:48 +08:00
hoshi-hiyouga
6d954b2733 Update utils.py
Former-commit-id: c9828f4c6e6c150c884e02d0213dff0c09801e77
2024-04-16 17:30:12 +08:00
hoshi-hiyouga
5226c4fa97 Update trainer.py
Former-commit-id: 6700a1b9fa0cbd965ac45d3f2de1088727235c25
2024-04-16 17:29:52 +08:00
Jonery
b3260c7456 resolve gradient checkpointing issue.
Former-commit-id: 7ecb61822b37f5d71060d696495830ff98edaa06
2024-04-16 12:05:27 +08:00
Jonery
025f329445 Feature BAdam
Former-commit-id: 06c8908d3fe48907ddb585c5fa15677fc5416f94
2024-04-15 23:15:27 +08:00
hiyouga
fb385b8c26 update examples
Former-commit-id: cce52351b54f70904f33902d9c17411134f9f6eb
2024-04-15 22:14:34 +08:00
hiyouga
9e7b460b2d fix model card
Former-commit-id: c53a11b6fd477fffb2030a4e3aeb4a56fd21e7a6
2024-04-12 17:11:59 +08:00
hiyouga
c9d3cc181a fix #3238
Former-commit-id: 232642a6215de9b57a1627f39b4efea127948a01
2024-04-12 14:28:11 +08:00
hiyouga
2ecf2bcbf0 fix resize vocab at inference #3022
Former-commit-id: 148bda353f0b53af022c51da9a9e59a56f341510
2024-04-03 18:14:24 +08:00
hiyouga
88d9f47a0b fix #3116
Former-commit-id: ce77d98872fa377fd4bc961701b07982f4b51491
2024-04-03 14:47:59 +08:00
hiyouga
bf5ffeeae0 simplify readme
Former-commit-id: 92dab8a90bdd82a72a06559943467b56dde12c71
2024-04-02 20:07:43 +08:00
hiyouga
829cf6458a fix #3083
Former-commit-id: 4a6ca621c09d179561acc5957c8c911a4e44184c
2024-04-01 22:53:52 +08:00
hiyouga
bd52e2b404 fix ORPO loss
Former-commit-id: 816d71414617590f95de89a49f38358e597ed121
2024-04-01 14:42:41 +08:00
hiyouga
69e1d39832 fix IPO and ORPO loss
Former-commit-id: 5b9b40403d59982431a526e337f31d394f8b882b
2024-04-01 14:37:53 +08:00
hiyouga
e7ade84bba fix plots
Former-commit-id: 5907216a1cc7a75a43d681ede410c2fba7fb7b92
2024-03-31 19:43:48 +08:00
hiyouga
b873dcb09d use log1p in orpo loss
https://github.com/huggingface/trl/pull/1491

Former-commit-id: 68aaa4904b8dfb6cc791fdcee613edc681a8a198
2024-03-31 19:27:08 +08:00
hiyouga
2f878bde11 support ORPO
Former-commit-id: 17bf8a2c3a7bb5b83071c8659cfd8751e894e692
2024-03-31 18:29:50 +08:00
marko1616
67c05c2031 Fix Llama model save for full param train
Former-commit-id: eb178eaff390a1dc342cc35ab8c7820d654f3717
2024-03-30 23:45:04 +08:00
hiyouga
fc066cad7f release v0.6.1
Former-commit-id: ca793028c69433eae405009c5ebb790c6c2d40c4
2024-03-29 11:36:08 +08:00
hiyouga
e4f3d583df fix #2982
Former-commit-id: 8d603f8820efd1617557f2bc5d9674143abe7c57
2024-03-28 20:22:31 +08:00
hiyouga
89c400633a update trainers
Former-commit-id: 8c77b1091296e204dc3c8c1f157c288ca5b236bd
2024-03-28 18:16:27 +08:00
hoshi-hiyouga
ae9ad13f2a fix ds optimizer
Former-commit-id: 3bcd41b639899e72bcabc51d59bac8967af19899
2024-03-26 23:39:56 +08:00
hiyouga
ec94e5e876 fix #2961
Former-commit-id: 511f6754026fbbf48bd481018015338a6a3ad92f
2024-03-26 17:26:14 +08:00
hiyouga
62312716d9 release v0.6.0 (real)
Former-commit-id: ba70aca8fb1275ed3b6af69a7e639303d7201da4
2024-03-25 23:37:48 +08:00
hiyouga
27151b8c65 release v0.6.0
Former-commit-id: 6f2b563f125fe51ee32753e58f902a4911ab757c
2024-03-25 22:38:56 +08:00
hiyouga
2d73831177 tiny fix
Former-commit-id: 558a538724db373319a6bba26c76943bac1b5063
2024-03-25 21:18:08 +08:00
marko1616
1d0e24549f pass ruff check
Former-commit-id: c8f0d99704308ac1886b16e437dea601eb20658d
2024-03-24 16:12:10 +08:00
marko1616
a68101cbbb fix Llama lora merge crash
Former-commit-id: 6f080fdba3f99145b7722964dd027179dc2eeb2b
2024-03-24 03:06:11 +08:00
marko1616
645c27e5e2 fix Llama lora merge crash
Former-commit-id: 51349ea1ccbf3e53b408037986abd850a0963468
2024-03-24 02:55:23 +08:00
marko1616
c083708433 fix Llama lora merge crash
Former-commit-id: c1e2c4ea45ad210e776a192e05e226b34d764135
2024-03-24 02:44:35 +08:00
hiyouga
8717e98200 fix #2777 #2895
Former-commit-id: 9bec3c98a22c91b1c28fda757db51eb780291641
2024-03-20 17:59:45 +08:00
hiyouga
3d483e0914 fix packages
Former-commit-id: 8e04794b2da067a4123b9d7091a54c5647f44244
2024-03-17 22:32:03 +08:00
hiyouga
06860e8f0f fix export
Former-commit-id: 6bc2c23b6d26b52f54ac37fa6149e6eb3cc18ee6
2024-03-15 15:06:30 +08:00
hiyouga
7ef49586be tiny fix
Former-commit-id: 6ebde4f23e761b8a3e3ea6ca6dff249e657608a1
2024-03-14 21:19:06 +08:00
hiyouga
2cf95d4efe fix export
Former-commit-id: 3b4a59bfb1866a270b9934a4a2303197ffdab531
2024-03-14 18:17:01 +08:00
hiyouga
edd28dbe2c fix bug
Former-commit-id: 8172530d54fbd42a9dd3219f06378563d62424e0
2024-03-13 23:55:31 +08:00
hiyouga
9ff7c99eb1 fix bug
Former-commit-id: 714d936dfbe022c4f2cfa6ff643e3482a3f96012
2024-03-13 23:43:42 +08:00
hiyouga
8b8671817f improve lora+ impl.
Former-commit-id: 72367307dfadf936fb989ebe8bc9f0ff229fb933
2024-03-13 23:32:51 +08:00
齐保元
24c9277488 [FEATURE]: ADD LORA+ ALGORITHM
Former-commit-id: a0965cd62c85545aa2364e244295df2963308354
2024-03-13 19:43:27 +08:00
hiyouga
c88062347e fix #2775
Former-commit-id: e874c00906c765b81c0e5ff9c7b3679557da8e0e
2024-03-11 00:42:54 +08:00
hiyouga
4a4e4b4354 support layerwise galore
Former-commit-id: 8664262cde3919e10eaecbd66e8c5d356856362e
2024-03-10 00:24:11 +08:00
hiyouga
868444e124 allow non-packing pretraining
Former-commit-id: bdb496644ce2c18806fc4fdae1fedcb3e5b5f808
2024-03-09 22:21:46 +08:00
hiyouga
1173441661 fix #2766
Former-commit-id: 412c52e325660e8b871ffd59f5564f84f46a143f
2024-03-09 21:35:24 +08:00
hiyouga
c561b268ef fix #2756 , patch #2746
Former-commit-id: e8dd38b7fdf8e172745d2538eb103895f2839c38
2024-03-09 02:01:26 +08:00
hiyouga
5b50458acf fix galore
Former-commit-id: 33a4c24a8a3c153bc62edf74b9246699a0ae3233
2024-03-08 00:44:51 +08:00
hiyouga
2c010c72b8 support galore
Former-commit-id: 28f78621883917425fabe49f5473778111012127
2024-03-07 22:41:36 +08:00
hiyouga
31c618f1f7 tiny fix
Former-commit-id: 0048a2021e94d068f7c6054df0b9569ae4912eb1
2024-03-06 17:25:08 +08:00