119 Commits

Author SHA1 Message Date
hiyouga
422cabc3f8 update loader
Former-commit-id: 080d8eab858217ca58bffe719d5ffde7579c5bda
2023-12-24 19:10:23 +08:00
hiyouga
52a348cac2 update patcher
Former-commit-id: d6d7b6670847ce4ea10353c5b126214542b45c2b
2023-12-23 15:24:27 +08:00
hiyouga
e5ce6c5098 fix unsloth dtype
Former-commit-id: fd22e6546ce5f38a6a075cf894aafc3d206b2fcd
2023-12-23 01:59:49 +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
ShaneTian
c905313429 Fix slow model initialization in bfloat16 dtype.
Former-commit-id: cf2e2f6f9b7f09b1e2faf6fbc413e3f62e3846c7
2023-12-22 16:27:28 +08:00
hiyouga
a7166f131e fix ds zero3 check
Former-commit-id: 7f50705b1d821d287bd854211319f697f57b25db
2023-12-21 01:19:22 +08:00
hiyouga
da5dbc107a match version
Former-commit-id: 16db52522584a8e084d4db2a7c253c8b88f27371
2023-12-20 22:17:35 +08:00
hiyouga
90c3549164 improve quantization
Former-commit-id: 4dde60017ad8208dfea0b2bb61df6a14a35d03e0
2023-12-20 18:27:16 +08:00
hiyouga
ddf6897b0a add max_memory for gptq #1923
Former-commit-id: 9afc42c8b999fbbc206d9a467ca5795b27a10096
2023-12-20 18:15:17 +08:00
hiyouga
7006512038 fix mixtral inference #1821
Former-commit-id: 612f9fd19cbd29e8b1785a1576a9668e7dcd264c
2023-12-20 15:11:15 +08:00
hiyouga
592c082b54 fix #1900
Former-commit-id: 4c35214396f873588562606b084740b6581188d9
2023-12-19 17:21:46 +08:00
hiyouga
67e284b2e4 fix #1742
Former-commit-id: efbb32afdcf0d6aa4ca26f54c95f76dbb84f77dc
2023-12-16 20:50:45 +08:00
hiyouga
a871c7d023 add noisy mean initialization #1815
Former-commit-id: 3253b1fca0123071913079277186c160046edf21
2023-12-16 19:47:51 +08:00
hiyouga
3eec0052cc support dpo-ftx
Former-commit-id: 86dfa04f9821556019fa777106787f73eb70b452
2023-12-16 19:21:41 +08:00
hiyouga
cedf58978e support autogptq in llama board #246
Former-commit-id: fea01226703d1534b5cf511bcb6a49e73bc86ce1
2023-12-16 16:31:30 +08:00
hiyouga
a08089f449 support quantization in export model
Former-commit-id: f32500ae6edccab7d14df4c92467e15986866def
2023-12-15 23:44:50 +08:00
hiyouga
ef730c23e2 update dc link
Former-commit-id: f6789e50e17a377b6d9b434d8e12ad99d8eecfeb
2023-12-15 22:11:31 +08:00
hiyouga
39263016cf fix bug
Former-commit-id: 95ac272907a04a64785f928536de1fd099150f92
2023-12-15 21:54:02 +08:00
hiyouga
9dd7249690 fix bug
Former-commit-id: 8b80baf02cfece53527c27712f0899fa3532c414
2023-12-15 21:49:26 +08:00
hiyouga
a993125740 add configurer
Former-commit-id: c40c9889615ffb49c7ce24c69c0d3d20d841c800
2023-12-15 21:46:40 +08:00
hiyouga
8432e50396 refactor adapter hparam
Former-commit-id: f82aece9ebd6df83a7a005cc7cbbcec07fa6e14d
2023-12-15 20:53:11 +08:00
hiyouga
df8341c931 add loftq
Former-commit-id: 0b900882ef19ac49604a24fbae8b3254f1bff7ad
2023-12-14 21:53:56 +08:00
hiyouga
511f3f68e2 fix valuehead model
Former-commit-id: 9f628debb6510f2d1c91b00f121a721ab5d648e9
2023-12-14 20:15:20 +08:00
hoshi-hiyouga
c9ff152cef tiny fix
Former-commit-id: 987df4c62f34026adfe2089910f4ff9ac6ebd9a6
2023-12-13 17:32:36 +08:00
hoshi-hiyouga
9793e4c4a8 revert peft version
Former-commit-id: 6440fa1a8c28fd2db58d0905a67d071837e0edd1
2023-12-13 10:49:45 +08:00
hoshi-hiyouga
0815793173 update peft version
Former-commit-id: 31c01e1272bd2cd9588e5ee68c1924a3dd55c67e
2023-12-13 10:23:51 +08:00
hoshi-hiyouga
cfde6f5594 tiny fix
Former-commit-id: 1478bc052417e0939188f55a0adcbf00956960f2
2023-12-13 10:21:29 +08:00
hoshi-hiyouga
a96df61024 fix #1819
Former-commit-id: f2e2b0354cbe9a7190ccab807f690cc8ab433a6e
2023-12-13 10:14:01 +08:00
hiyouga
8dc554a56b remove loftq
Former-commit-id: e175c0a1c631296117abda2403a4b87bbdd35a66
2023-12-13 01:53:46 +08:00
hiyouga
0507637911 support loftq
Former-commit-id: e7ac2eb7f7daae17525a278ffbe2f82c0fbd8093
2023-12-12 22:47:06 +08:00
hiyouga
d9f621be13 support system column #1765
Former-commit-id: f425584a511c5e42bae8b3ba090eaa898b28adad
2023-12-12 19:45:59 +08:00
hiyouga
aa30233322 fix modelscope data hub
Former-commit-id: 5b63e8c22538a4788e4b6c8df50e6e6be93ceeac
2023-12-12 18:33:06 +08:00
hiyouga
e88b100ce2 update readme
Former-commit-id: 42e042a4206aeb5177ddde56386e9655b0c06460
2023-12-12 11:44:30 +08:00
hiyouga
82592501be support mixtral
Former-commit-id: 75b5b8e36ab1933b2625f11b645f56cbc805fd85
2023-12-12 11:39:04 +08:00
hiyouga
d75327e786 fix baichuan resize
Former-commit-id: 66956d13074a9bc74d7a737b9476f38361a7764a
2023-12-11 20:55:50 +08:00
hiyouga
903cc3dcc1 tiny fix
Former-commit-id: 1f839fc4f278c2a258df22899241fc66a2cca682
2023-12-11 18:09:40 +08:00
hiyouga
51de180a2e support resize embeddings #1786
Former-commit-id: 368a41bd3c6a04f869083058d9165954fbdad105
2023-12-11 17:50:02 +08:00
hiyouga
02b5f23266 use peft 0.7.0, fix #1561 #1764
Former-commit-id: 423947bd58aa50da8785b8ceca1e7e288447a9da
2023-12-11 17:13:40 +08:00
hiyouga
14f7ea1185 fix #1771 and temporarily fix #1764
Former-commit-id: d0e5a5d604e16c2fe0035b0ac1d54dc3625d4da3
2023-12-08 16:26:20 +08:00
hiyouga
cf70644f8f fix #1715
Former-commit-id: 3f9192dbbbafdc2171d2eb80282d5cae47565b7b
2023-12-03 22:35:47 +08:00
hiyouga
74851e7033 implement rm server #1543
Former-commit-id: 2e5bb6888c86079493456c2ddd525f8c52b9963e
2023-12-03 20:52:54 +08:00
hiyouga
9bf0dcfe39 fix #1707 #1710
Former-commit-id: 243a596518ad69cf1eec20a082534b9e94353ce4
2023-12-03 11:33:12 +08:00
hiyouga
823a75ef22 fix #1642
Former-commit-id: 11be28201f688ac21cf94135067d37e9aa7ab0a1
2023-12-02 00:37:53 +08:00
hiyouga
d46ce88519 fix gptq training
Former-commit-id: bec58e3dc575aa4247e563881a456328ee5ef496
2023-12-02 00:27:15 +08:00
hiyouga
c58714b9b0 tiny fix
Former-commit-id: fd2782a06ba4efa76cacbb49eb76a05de8d8aca6
2023-12-01 23:37:10 +08:00
hiyouga
3f4a397105 fix gptq model inference
Former-commit-id: f7da9a87cb48cacb7d56322817b05d6f471f6508
2023-12-01 23:34:14 +08:00
hiyouga
caf4fa46e0 patch modelscope
Former-commit-id: 8888cf53f040f5a2d8c0e59cddf79b252449bf58
2023-12-01 22:53:15 +08:00
yuze.zyz
b8ee512ec2 add readme
Former-commit-id: 3d5ec6f12b4ae7d04520e6865516a9a6dd4f7efe
2023-12-01 16:11:30 +08:00
yuze.zyz
20ff344a57 fix
Former-commit-id: e8774b4c9cbc8f894621ec72957f720d5c83d22b
2023-11-29 21:43:58 +08:00