Commit Graph

1126 Commits

Author SHA1 Message Date
hoshi-hiyouga
17975fefd7 Update tuner.py
Former-commit-id: 13851fb045
2024-05-11 23:54:53 +08:00
BUAADreamer
c3e15c049b Merge branch 'main' of https://github.com/BUAADreamer/LLaMA-Factory
Former-commit-id: 7944cbc576
2024-05-11 13:11:10 +08:00
BUAADreamer
743d0f22b7 add full parameter finetuning of mllm
Former-commit-id: 7be7972f28
2024-05-11 13:11:00 +08:00
kkkl
639c6e9cad Update constants.py
Fix the download issue of the Phi3 model

Former-commit-id: b5c5c315a5
2024-05-11 00:22:40 +08:00
BUAADreamer
012d93da84 Merge branch 'hiyouga:main' into main
Former-commit-id: 508d474754
2024-05-10 20:34:41 +08:00
hiyouga
9dc209b458 resolve python 3.8 package
Former-commit-id: 75aec4cf8e
2024-05-09 16:52:27 +08:00
Tendo33
dd42439b03 1.Change the name of is_fastapi_available function
2. Added the log of printing requests when deploying using vllm


Former-commit-id: fd2e6dec58
2024-05-09 14:28:01 +08:00
BUAADreamer
a185cf7e18 add push processor to hub
Former-commit-id: 8b997e32fb
2024-05-09 14:05:19 +08:00
BUAADreamer
db30e9089a Merge branch 'hiyouga:main' into main
Former-commit-id: 83f2f0de1d
2024-05-09 13:45:43 +08:00
cocktailpeanut
2370e7403f yet another removal of unnecessary environment variables
Former-commit-id: 3c11157a49
2024-05-09 01:33:20 -04:00
cocktailpeanut
58c5a5afaf more removal of unnecessary environment variables
Former-commit-id: 425b9d6166
2024-05-09 01:32:00 -04:00
cocktailpeanut
de509fa081 remove unnecessary environment variable usage
Former-commit-id: b783673e0a
2024-05-09 01:26:15 -04:00
BUAADreamer
f40b602c41 add mllm export
Former-commit-id: ef33856380
2024-05-08 22:50:42 +08:00
hiyouga
5ff89a0f32 fix #3625
Former-commit-id: d9cdddd19c
2024-05-08 17:12:56 +08:00
hiyouga
0000894bbe add llama3 chinese chat
Former-commit-id: 48ee46dac1
2024-05-08 17:10:03 +08:00
hiyouga
1d3fb90590 add deepseek moe 236B
Former-commit-id: 10ab83f4c4
2024-05-08 16:37:54 +08:00
BUAADreamer
3534a75bcc modify export model
Former-commit-id: 0ca1d1967d
2024-05-08 10:36:36 +08:00
hiyouga
57fee01114 fix #3560
Former-commit-id: 0f8f7d3b90
2024-05-07 19:03:35 +08:00
hiyouga
52cc6bce38 fix #3602
Former-commit-id: b0888262e3
2024-05-07 17:50:27 +08:00
hiyouga
175a7ea951 fix stop param
Former-commit-id: 09f3ef1de4
2024-05-07 00:41:04 +08:00
hoshi-hiyouga
c198db4db2 Merge pull request #3527 from zhaonx/dev
"add support for vllm api stop parameter"

Former-commit-id: bcf7ec5ceb
2024-05-07 00:37:49 +08:00
hoshi-hiyouga
df66b288a2 Update vllm_engine.py
Former-commit-id: 17d0005b8c
2024-05-07 00:37:05 +08:00
hoshi-hiyouga
4c91104471 Update generating_args.py
Former-commit-id: f32eefae3d
2024-05-07 00:28:16 +08:00
hoshi-hiyouga
d65b2332cf Update generating_args.py
Former-commit-id: 7ae7ae64f0
2024-05-07 00:27:56 +08:00
hiyouga
89e7cabaa9 fix gradio args
Former-commit-id: a153039380
2024-05-06 23:33:06 +08:00
hiyouga
eb21a527a6 update docs
Former-commit-id: 34d33e2257
2024-05-06 21:47:00 +08:00
zhouwei
7b0629dac4 The training efficiency of the Ascend 910A has been significantly enhanced, leveraging the full computational power of the NPU (Neural Processing Unit) and the capabilities of torch_npu, a PyTorch library optimized for NPUs. This improvement has resulted in a remarkable tenfold increase in efficiency.
Former-commit-id: 28ae947161
2024-05-06 13:29:59 +08:00
zhaonx96
189346188b ”add stop parameter in chat.py“
Former-commit-id: 80645751bc
2024-05-06 10:10:00 +08:00
zhaonx96
0c6c50f9b5 Merge branch 'main' of https://github.com/zhaonx/LLaMA-Factory into dev
Former-commit-id: 1abd55dd59
2024-05-06 10:09:00 +08:00
hiyouga
fa9c7eb48e add version and help to cli
Former-commit-id: bd095eeb73
2024-05-05 02:44:35 +08:00
hiyouga
9bbb5c846d update webui
Former-commit-id: af596988b1
2024-05-05 00:17:54 +08:00
hiyouga
87b9f70ab4 remove empty stream response
Former-commit-id: e984ba3167
2024-05-04 16:13:52 +08:00
hiyouga
6672ad7a83 fix async stream api response
Former-commit-id: 941924fdbd
2024-05-04 16:11:18 +08:00
hiyouga
c32fc1d89b update api and support abort eval in webui
Former-commit-id: ed8f8be752
2024-05-04 15:59:15 +08:00
hiyouga
ed92038736 update readme and webui launch
Former-commit-id: 9d2ce57345
2024-05-04 00:43:02 +08:00
hiyouga
9fc7549d25 fix eval in webui
Former-commit-id: 24cc93ab15
2024-05-04 00:19:19 +08:00
hiyouga
340f70cd82 fix webui resume
Former-commit-id: 510e64ee70
2024-05-03 23:15:19 +08:00
hiyouga
226587fc4a fix slow op in dpo/orpo trainer
Former-commit-id: 3010154adb
2024-05-03 23:06:52 +08:00
hiyouga
a2cb40735b fix callback log multigpu #3559
Former-commit-id: 9585838ebe
2024-05-03 21:24:27 +08:00
hiyouga
65abcf1a94 enable tqdm in webui
Former-commit-id: 5e6f808e3c
2024-05-03 04:42:50 +08:00
hiyouga
59965c2dca fix gen_args
Former-commit-id: 17d2e5147e
2024-05-03 04:24:50 +08:00
hiyouga
572d25734a fix colab gradio
Former-commit-id: 530f6b49bb
2024-05-03 03:54:46 +08:00
hiyouga
289d1f3679 update webui and add CLIs
Former-commit-id: 245fe47ece
2024-05-03 02:58:23 +08:00
hiyouga
ed8d9e0881 fix badam configs
Former-commit-id: 9433c8c215
2024-05-02 02:47:04 +08:00
hoshi-hiyouga
1d00dede8e Update train.py
Former-commit-id: dcd53cb89a
2024-05-02 02:21:27 +08:00
zhaonx
4a0aab86f1 "add support for vllm api stop parameter"
Former-commit-id: 42edc81585
2024-04-30 17:17:09 +08:00
codingma
ac76a9e140 support BAdam in WebUI
Former-commit-id: 26f7170393
2024-04-28 11:31:34 +08:00
hiyouga
506f868de7 fix llava rlhf
Former-commit-id: b3e33c703e
2024-04-28 03:01:49 +08:00
hiyouga
3b42f1abce add models to 0.7.0
Former-commit-id: 4dbbce21d5
2024-04-28 01:50:30 +08:00
hiyouga
eb14501a52 release v0.7.0
Former-commit-id: 168f56683a
2024-04-26 23:18:00 +08:00