876 Commits

Author SHA1 Message Date
hiyouga
f869e44fe5 fix #1909
Former-commit-id: 3e93c33af9f80e28c9f30af9b7ba20757358afb4
2023-12-23 14:42:20 +08:00
hiyouga
bcc92919a0 update readme
Former-commit-id: d3dea7a926e9d356a39ca2033b03be7f559cc143
2023-12-23 02:17:41 +08:00
hiyouga
306a70c7ba fix unsloth dtype
Former-commit-id: fd22e6546ce5f38a6a075cf894aafc3d206b2fcd
2023-12-23 01:59:49 +08:00
hiyouga
d358d955e5 fix dpo trainer
Former-commit-id: c160dd7cd86e296e32775ace2e4258a473449c41
2023-12-23 01:51:55 +08:00
hiyouga
0fdd6074c3 llama board: add unsloth
Former-commit-id: 9477e6f28808ae9deadada1f6cf679a29542c271
2023-12-23 00:35:53 +08:00
hiyouga
6faf9c35a9 support unsloth
Former-commit-id: b857f00234b90b785d82ca7cdb29af3d948b1a7b
2023-12-23 00:14:33 +08:00
hoshi-hiyouga
1066898e32 Merge pull request #1953 from ShaneTian/model-load-bf16
Fix slow model initialization in bfloat16 dtype.

Former-commit-id: 69daf107c4561f807ceae066f04d432323699cef
2023-12-22 17:29:54 +08:00
ShaneTian
d05febe5de Fix slow model initialization in bfloat16 dtype.
Former-commit-id: cf2e2f6f9b7f09b1e2faf6fbc413e3f62e3846c7
2023-12-22 16:27:28 +08:00
hiyouga
67f7034a21 fix param type
Former-commit-id: 11b99f344416ade1cdac52e11ba7f36fcf689221
2023-12-21 17:33:01 +08:00
hiyouga
79f301a2c6 fix ds zero3 check
Former-commit-id: 7f50705b1d821d287bd854211319f697f57b25db
2023-12-21 01:19:22 +08:00
hiyouga
31cbc67986 match version
Former-commit-id: 16db52522584a8e084d4db2a7c253c8b88f27371
2023-12-20 22:17:35 +08:00
hoshi-hiyouga
fe66bf3663 Merge pull request #1932 from ShaneTian/main
Update transformers to 4.36.2 to resolve multi-node saving bug.

Former-commit-id: 5c55907a57e8327134e2c982c838a53c9fa42f51
2023-12-20 22:13:28 +08:00
ShaneTian
4691d4b35d Update transformers to 4.36.2 to resolve bug when saving a checkpoint in the multi-node setting.
Former-commit-id: 3173f8e51eec5e8f488e3dfc54ad371b640d6b87
2023-12-20 22:00:41 +08:00
hiyouga
acf5241845 fix stop words
Former-commit-id: 6ce6cac9fa8f0af33697e824cf93a9a80cdbd064
2023-12-20 19:06:43 +08:00
hiyouga
2bce99b82f fix yi template #1895
Former-commit-id: 05b4fa1e2b13a15ee261a151ac8cd0a2ebdf5edc
2023-12-20 18:58:16 +08:00
hiyouga
3c330869ef improve quantization
Former-commit-id: 4dde60017ad8208dfea0b2bb61df6a14a35d03e0
2023-12-20 18:27:16 +08:00
hiyouga
dba1af4841 add max_memory for gptq #1923
Former-commit-id: 9afc42c8b999fbbc206d9a467ca5795b27a10096
2023-12-20 18:15:17 +08:00
hiyouga
2b1e52dcc9 fix #1073 #1462 #1735 #1908
Former-commit-id: cd8e2535aa66931b24b96e76c2b56ce703a579b1
2023-12-20 17:15:40 +08:00
hiyouga
b5238e945a optimize data loading logic
Former-commit-id: 58f669b384582ac90e85de835f1f44f7003f9ec0
2023-12-20 16:15:41 +08:00
hiyouga
afc0f29704 fix #1909
Former-commit-id: f563e8d28dfa48a60cbe3d295b20f9cf58de296d
2023-12-20 16:11:07 +08:00
hiyouga
de0bb1d2da fix mixtral inference #1821
Former-commit-id: 612f9fd19cbd29e8b1785a1576a9668e7dcd264c
2023-12-20 15:11:15 +08:00
hiyouga
cc16ece283 fix #1900
Former-commit-id: 4c35214396f873588562606b084740b6581188d9
2023-12-19 17:21:46 +08:00
hiyouga
31ba802fc9 update readme
Former-commit-id: 36cd747e6a1a568e1a03e6c6611fec48e6ab9df7
2023-12-18 22:29:45 +08:00
hiyouga
4b27cf5460 add codegeex template
Former-commit-id: a8222722b8097158f1c92e3729f41d411eff3926
2023-12-18 19:52:35 +08:00
hiyouga
a53b2a643f add xverse-65B-2 model
Former-commit-id: 3e563a0d9666934dfdab54d61654ec00079a93f1
2023-12-18 19:24:09 +08:00
hiyouga
d925ecae1b add models
Former-commit-id: 3a4728557304996bcbe58d7d6380beead7c63c70
2023-12-18 19:09:31 +08:00
hiyouga
13fd751a78 fix tokenizer for Yi chat models #1617 #1875
Former-commit-id: 9485692c8d367a0b25d3e653db413aa01cb9ad7d
2023-12-18 17:18:11 +08:00
hiyouga
74575f8922 update readme
Former-commit-id: 01267eee0da0bffb3f0c0378e2e60d14e05585c4
2023-12-18 15:46:45 +08:00
hiyouga
5e7bb5fe73 fix llama board
Former-commit-id: f43f61b2898dda56aba0066fcb3409b152260bdb
2023-12-16 22:17:37 +08:00
hiyouga
790a31404a fix #1742
Former-commit-id: efbb32afdcf0d6aa4ca26f54c95f76dbb84f77dc
v0.4.0
2023-12-16 20:50:45 +08:00
hiyouga
f927601702 add xverse-65b-chat model
Former-commit-id: fff6288db6b61ca27010ea47c918298f76922106
2023-12-16 20:21:29 +08:00
hiyouga
c4654d54d7 set version
Former-commit-id: 45a05e3a415eeaf875e2cf15bdba0235fbd7d527
2023-12-16 20:17:51 +08:00
hiyouga
df777c30d1 add noisy mean initialization #1815
Former-commit-id: 3253b1fca0123071913079277186c160046edf21
2023-12-16 19:47:51 +08:00
hiyouga
d81ad2d4bc support dpo-ftx
Former-commit-id: 86dfa04f9821556019fa777106787f73eb70b452
2023-12-16 19:21:41 +08:00
hiyouga
9f77e8b025 support autogptq in llama board #246
Former-commit-id: fea01226703d1534b5cf511bcb6a49e73bc86ce1
2023-12-16 16:31:30 +08:00
hoshi-hiyouga
04dc3f4614 Merge pull request #1868 from yhyu13/improve_hfargparser
Improve logging for unknown args

Former-commit-id: 6455013a99ca5c63f5b99c1100e93f794a03c497
2023-12-16 16:06:09 +08:00
yhyu13
7d1fe50977 Use llmtuner logger
Former-commit-id: ef5a560b4246e04e0ef2612e3520e05288e93707
2023-12-16 07:15:27 +00:00
yhyu13
c0e5e3c5d5 Improve logging for unknown args
Former-commit-id: 03e49d76ca91f7fcaf1c013740d5f6bfc11a2028
2023-12-16 05:16:29 +00:00
hiyouga
3a45cfb604 update tips
Former-commit-id: 4432cbda6b7535bcbb40ba77df069fca631b4be8
2023-12-15 23:52:50 +08:00
hiyouga
393e4b0f5a fix #1770
Former-commit-id: 8266187cec70bb4bd1b4837d51b09409ec11f93e
2023-12-15 23:50:15 +08:00
hiyouga
296711d502 support quantization in export model
Former-commit-id: f32500ae6edccab7d14df4c92467e15986866def
2023-12-15 23:44:50 +08:00
hiyouga
9121722999 update dc link
Former-commit-id: f6789e50e17a377b6d9b434d8e12ad99d8eecfeb
2023-12-15 22:11:31 +08:00
hoshi-hiyouga
d8d74091f6 Merge pull request #1864 from hiyouga/dev
Refactor hyper-parameters of adapters and model loader

Former-commit-id: d5ce2fb6858b9f2963f355e9f4d6f046eb6efdcd
2023-12-15 22:06:56 +08:00
hiyouga
33521fb45e fix bug
Former-commit-id: 95ac272907a04a64785f928536de1fd099150f92
2023-12-15 21:54:02 +08:00
hiyouga
e5204e60ed fix bug
Former-commit-id: 8b80baf02cfece53527c27712f0899fa3532c414
2023-12-15 21:49:26 +08:00
hiyouga
0409428d87 add configurer
Former-commit-id: c40c9889615ffb49c7ce24c69c0d3d20d841c800
2023-12-15 21:46:40 +08:00
hiyouga
f902b0d420 refactor adapter hparam
Former-commit-id: f82aece9ebd6df83a7a005cc7cbbcec07fa6e14d
2023-12-15 20:53:11 +08:00
hiyouga
27ef5b1aa7 add loftq
Former-commit-id: 0b900882ef19ac49604a24fbae8b3254f1bff7ad
2023-12-14 21:53:56 +08:00
hiyouga
c32303fc7e fix valuehead model
Former-commit-id: 9f628debb6510f2d1c91b00f121a721ab5d648e9
2023-12-14 20:15:20 +08:00
hoshi-hiyouga
45abe361ba tiny fix
Former-commit-id: 987df4c62f34026adfe2089910f4ff9ac6ebd9a6
2023-12-13 17:32:36 +08:00