863 Commits

Author SHA1 Message Date
hiyouga
9537bc7f3e fix #1789
Former-commit-id: d86455f685fa531e651333e00b4fe54d895cf2e4
2024-01-09 18:31:27 +08:00
hiyouga
7c3311ad5a fix #2127
Former-commit-id: 5a1aa33fa9b546ab520f0ba4cb9d996b87eb71ca
2024-01-09 14:49:13 +08:00
hiyouga
326fe807fc fix #2125
Former-commit-id: 46a22f4daeafac5b0a695212d060960ff53af613
2024-01-08 21:42:25 +08:00
hoshi-hiyouga
0347f2c785 Merge pull request #2117 from dasdristanta13/main
Update requirements.txt With einops dependency

Former-commit-id: af0c05f1cffc7fc0fc74d514783333501f83f59e
2024-01-07 23:56:53 +08:00
Dristanta Das
745ee0d35f Update requirements.txt With einops dependency
Former-commit-id: 0b47b13cb34cace6fa0b6d0c58ca16fb01b3a5e9
2024-01-07 21:03:30 +05:30
hiyouga
e86b081fa6 tiny fix
Former-commit-id: 06b854fe15eb4cf4ff8d6f5570068d9e74a2f1b3
2024-01-07 17:17:18 +08:00
hiyouga
af5ba98df2 fix api server
Former-commit-id: cedd80ba56c0090487f65f4b1227e5615943997f
2024-01-07 17:14:42 +08:00
hiyouga
33f1141705 improve model export
Former-commit-id: 31255147a566a23ce1a48402662d14af8ac267ab
2024-01-05 18:51:49 +08:00
hiyouga
db73b834a0 fix #2098
Former-commit-id: e62d9158cffbf1044396597ddaf15b1c0bc5f954
2024-01-05 17:11:26 +08:00
hiyouga
0a69dad469 fix qwen template
Former-commit-id: c1923e0daa02b49ac07e96ce29877729acc78d31
2024-01-05 16:14:56 +08:00
hiyouga
fbd7510b9a fix #2081
Former-commit-id: ec4b539b6c0be11e15d273025c414b694bbd6c9a
2024-01-04 23:19:08 +08:00
hiyouga
53d24f5884 fix #2090
Former-commit-id: 13ec720990a88b01f7f5e2a99a87f95128dc3537
2024-01-04 23:05:08 +08:00
hiyouga
9e691856b4 fix #2067
Former-commit-id: 6cfdeea5261fd5bf6f91ba2bb3efb921a2f3e866
2024-01-04 22:53:03 +08:00
hiyouga
9272e0276b fix dispatch
Former-commit-id: deda82638716506dc690902c51276bb1eb0ddd5e
2024-01-03 16:33:16 +08:00
hiyouga
62a47bffdb fix valuehead patch
Former-commit-id: d9cb98362b58b28ae0ee207e7c07e75e5d810876
2024-01-03 16:19:23 +08:00
hiyouga
4f6c841d52 fix rm server
Former-commit-id: 81bc1638682a9fd01518f9f25250a6b584d2a9e6
2024-01-03 15:30:46 +08:00
hiyouga
f4d2860391 fix #2014
Former-commit-id: 077f6bf64e50f01f62aa4a957438bedc4e7925b3
2023-12-29 15:17:22 +08:00
hiyouga
e730c45072 add yuan model
Former-commit-id: 6a0377e2e51633bd5fb10fa8628e554565c5ee3e
2023-12-29 13:50:24 +08:00
hiyouga
e058832486 fix version
Former-commit-id: dd7500b65d0d548441eece101b60d51fa619cc0f
2023-12-29 04:53:36 +08:00
hiyouga
512a086221 fix args
Former-commit-id: ff18f327a3dc96d9677ef32841e8f29ab2eeb7ef
2023-12-28 18:47:19 +08:00
hiyouga
e25016cc6b fix export format
Former-commit-id: 7c82bd396b9e6ff395850ad544d95cbf1b7557cd
2023-12-28 18:40:46 +08:00
hiyouga
bb4e62cbcd fix ppo trainer
Former-commit-id: ca5b5823b03822ef899405d233a82396be997f44
2023-12-28 18:09:28 +08:00
hiyouga
01195b5e22 add model link
Former-commit-id: 159729929516f68aa1f43a852ed50ca0fac81523
2023-12-25 19:44:38 +08:00
hiyouga
6298f4779c tiny update
Former-commit-id: 4417b8ee20b381c964f452f52081667dfa33cd7b
2023-12-25 18:29:34 +08:00
hiyouga
ea6d219fc0 fix bug
Former-commit-id: b06faa1be3f5aa5e0fa31aa31314c213c36c3442
2023-12-24 19:20:12 +08:00
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
675a43d797 fix #1909
Former-commit-id: 3e93c33af9f80e28c9f30af9b7ba20757358afb4
2023-12-23 14:42:20 +08:00
hiyouga
ebf4786979 update readme
Former-commit-id: d3dea7a926e9d356a39ca2033b03be7f559cc143
2023-12-23 02:17:41 +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
c190793164 llama board: add unsloth
Former-commit-id: 9477e6f28808ae9deadada1f6cf679a29542c271
2023-12-23 00:35:53 +08:00
hiyouga
9cdaa43d1c support unsloth
Former-commit-id: b857f00234b90b785d82ca7cdb29af3d948b1a7b
2023-12-23 00:14:33 +08:00
hoshi-hiyouga
74ed80625c 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
c905313429 Fix slow model initialization in bfloat16 dtype.
Former-commit-id: cf2e2f6f9b7f09b1e2faf6fbc413e3f62e3846c7
2023-12-22 16:27:28 +08:00
hiyouga
b616365c4b fix param type
Former-commit-id: 11b99f344416ade1cdac52e11ba7f36fcf689221
2023-12-21 17:33:01 +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
hoshi-hiyouga
57a2924249 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
2cacdaccf4 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
ff45025585 fix stop words
Former-commit-id: 6ce6cac9fa8f0af33697e824cf93a9a80cdbd064
2023-12-20 19:06:43 +08:00
hiyouga
f08efeab48 fix yi template #1895
Former-commit-id: 05b4fa1e2b13a15ee261a151ac8cd0a2ebdf5edc
2023-12-20 18:58:16 +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
869e54f39b fix #1073 #1462 #1735 #1908
Former-commit-id: cd8e2535aa66931b24b96e76c2b56ce703a579b1
2023-12-20 17:15:40 +08:00
hiyouga
b761e108f1 optimize data loading logic
Former-commit-id: 58f669b384582ac90e85de835f1f44f7003f9ec0
2023-12-20 16:15:41 +08:00
hiyouga
cb7e0ce94d fix #1909
Former-commit-id: f563e8d28dfa48a60cbe3d295b20f9cf58de296d
2023-12-20 16:11:07 +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
c51d29c36f update readme
Former-commit-id: 36cd747e6a1a568e1a03e6c6611fec48e6ab9df7
2023-12-18 22:29:45 +08:00