1198 Commits

Author SHA1 Message Date
hoshi-hiyouga
5f67fdaac9 Update loader.py
Former-commit-id: 19d8fd62c18ee3ba0e431fc241f7d315cb716fef
2024-05-30 00:12:12 +08:00
hoshi-hiyouga
05e6fe4287 Update parser.py
Former-commit-id: 310cc11e8c83f16fc5bccc349c38fea347ea9a97
2024-05-30 00:05:20 +08:00
hiyouga
87aa332583 better llamaboard
* easily resume from checkpoint
* support full and freeze checkpoints
* faster ui


Former-commit-id: 84cfb2452cc86b037ccddee6e833f8eb7c129fa4
2024-05-29 23:55:38 +08:00
hiyouga
f90c4ca672 fix cohere system
Former-commit-id: 5d629b29e705c8ff8dd4521719d9c0e67a3fe0a2
2024-05-29 20:58:23 +08:00
hiyouga
a922e85a5c fix #3965
Former-commit-id: 37d15ac55d0be0ff47d6a88f07e2d823117a4a36
2024-05-29 20:55:51 +08:00
hiyouga
9a65820592 update readme
Former-commit-id: 440e9de66986ef7736361ce8ec3e23ce68655a56
2024-05-29 18:39:11 +08:00
hzhaoy
29cb4a1327 add TeleChat-12B/TeleChat-12B-v2 models
Former-commit-id: e0675385c88af03aaef8d51586c8a282829c4051
2024-05-29 15:00:37 +08:00
hiyouga
81a61134b8 fix hf chat engine
Former-commit-id: 76ce52911690ab0dd8ffa5587127afb4ec942abe
2024-05-29 01:20:07 +08:00
hiyouga
cb1a49aa02 add ds config to webui
Former-commit-id: 66d72b263d36dc81de9f6152077663b613035977
2024-05-29 01:13:17 +08:00
hiyouga
351b4efc6c 10x generate in ppo w/ zero3
https://github.com/huggingface/trl/pull/1483

Former-commit-id: 5dc43ba8b373d8803bc22d88b3d0d95ef8b9c7f8
2024-05-29 00:23:23 +08:00
hiyouga
9b551309de update dpo, kto trainer
Former-commit-id: 4a6cc3c7046f8b27d05ea53ef216bab6fa7ebfaf
2024-05-29 00:14:29 +08:00
hiyouga
9fed4a2ef4 clean kto trainer
Former-commit-id: 76402bd78cbd3a99a544f0ac019468b569b0e1d1
2024-05-28 21:43:26 +08:00
hiyouga
bceac4f554 bump vllm version to 0.4.1
Former-commit-id: a00fd39a4c2f270620711f2bfbad8d460fb4aa89
2024-05-28 21:27:27 +08:00
hiyouga
ae3a88d3a7 update readme
Former-commit-id: bc861f76706df3f643028f1dfc8ec2044b067a08
2024-05-28 19:35:52 +08:00
hiyouga
9138a7a5ba support DDP in webui
Former-commit-id: d059262ff8dc857f597d2657546ec625726a664a
2024-05-28 19:24:22 +08:00
Yimi81
d9fbd675d5 fix yi template
Former-commit-id: b3669c8989c3adda305416245e32e9e5a3b7caac
2024-05-27 13:11:25 +00:00
hiyouga
0206e7b9de tiny fix
Former-commit-id: 4c47b3dcef9e400a1c35fce1ad53619a0a86fe81
2024-05-27 20:54:26 +08:00
hoshi-hiyouga
a886544d3d Merge pull request #3921 from gusye1234/main
Add openchat-3.6-8B support

Former-commit-id: 92e6bba3cab22b7835a68f787caf7992a398978e
2024-05-27 20:52:37 +08:00
hoshi-hiyouga
8c9b929bb0 Update template.py
Former-commit-id: f4dabce0a71c9978e051e70886941b64b928ffe2
2024-05-27 20:51:56 +08:00
hoshi-hiyouga
1bb1ae834e Update template.py
Former-commit-id: af869e4c48eb426c4078415533f6dab89123a9d8
2024-05-27 20:51:26 +08:00
Jianbai Ye
0d9e364a90 add openchat-3.6-8B support
Former-commit-id: b66f39d50d896d7597a1506e67ec210b31c9b700
2024-05-27 20:42:08 +08:00
hiyouga
3b28c003dd fix full/freeze tuning for mllm
Former-commit-id: df5860ddb593d5b82163a585d12160b41dbce0f3
2024-05-27 20:37:57 +08:00
hoshi-hiyouga
48ff9fb150 Merge pull request #3835 from BUAADreamer/main
fix some features in llava-style training

Former-commit-id: fc8583bd17dfb088a52e4d8fa91356b918373b50
2024-05-27 20:23:45 +08:00
hiyouga
c43bc74fe6 support Aya23
Former-commit-id: 071935b90006e2c79e39bb9ee0c5d48c6c910501
2024-05-27 20:23:24 +08:00
BUAADreamer
79bc60db33 Merge branch 'hiyouga:main' into main
Former-commit-id: d89e1f8bf8bad1dd125b4de8fe6c0b2b16411cb5
2024-05-27 19:00:48 +08:00
BUAADreamer
932f0d5c20 add regex of only tune lm and mm_proj
Former-commit-id: 38d540b3e69bceabafafab524fcfc78aeb05612d
2024-05-27 18:59:00 +08:00
hiyouga
9670f5e41a add phi-3 7b/14b, mistral v0.3 models
Former-commit-id: 86dab182f9710b063f518922ccb49b01aa71c576
2024-05-27 18:20:16 +08:00
hiyouga
97a23e1cbe update readme
Former-commit-id: b8d0170fe0d094acce85dcb5f91775e4685ee055
2024-05-27 18:14:02 +08:00
BUAADreamer
11fcd055ec Merge branch 'hiyouga:main' into main
Former-commit-id: 113be744b3d044fbea3a8654158aa83ddb4599eb
2024-05-27 11:54:01 +08:00
hiyouga
b0d9966663 support SimPO #3900
Former-commit-id: 6b954ce60155cf8334150b795cfc4bb63ca74c8b
2024-05-26 23:46:33 +08:00
BUAADreamer
5c51ab7e1f Merge branch 'hiyouga:main' into main
Former-commit-id: fd5420c43e1414bcd3fadb6239f4e5d42e6ac10e
2024-05-25 14:18:49 +08:00
hiyouga
26f293d587 fix #3853
Former-commit-id: 465a5500bae1f30744d4b9b3db40aaf9171da2cb
2024-05-24 23:29:45 +08:00
seanzhang-zhichen
a3b52fd380 Merge branch 'main' into add_dataset_sample_num
Former-commit-id: 26300127c45f24e63b91f1b0cc73e46c3a936a91
2024-05-24 15:57:47 +08:00
BUAADreamer
27d8706d6d Merge branch 'hiyouga:main' into main
Former-commit-id: a4ce5ee381fd59f6b254ab634af51b6bb54edd97
2024-05-24 09:50:00 +08:00
hiyouga
bf59383783 refactor data preprocessing, fix mllm rlhf
Former-commit-id: 53ff2dd24f9121ea30c95063bb72e49a9b31e980
2024-05-24 04:08:25 +08:00
hiyouga
e6fc0ac8fe fix paligemma sft
requires transformers>=4.41.1


Former-commit-id: 80b3030569cd606ac0de43e9a682478f5bd7b727
2024-05-24 00:23:40 +08:00
hiyouga
554ca3d8dc fix oom issues in export
Former-commit-id: b7ccc882a192aa1e25b1e5816f875ea304282412
2024-05-23 23:32:45 +08:00
BUAADreamer
c0e4475485 Merge branch 'hiyouga:main' into main
Former-commit-id: 4076f52c8ba7da4624a1fb3fa52a7170d1c3171e
2024-05-21 22:18:20 +08:00
hiyouga
2b65f8bd5c fix paligemma sft
Former-commit-id: 60682d04414be37e611d6470618a8d599703942b
2024-05-21 20:03:09 +08:00
hiyouga
4adec327de fix #3847
Former-commit-id: d206b306ca4eadc8b3d4feaf490ad12f9452e562
2024-05-21 17:53:06 +08:00
BUAADreamer
1f093334d1 support pretraining of llava
Former-commit-id: 6a4c8cf0a6a1674c693b9337f018ff8df7477f8f
2024-05-21 08:57:14 +08:00
hiyouga
e0e8507108 support paligemma
Former-commit-id: 11c27f9bf204d3d6a9ca5bd4f0a19a420160453f
2024-05-21 00:01:22 +08:00
hiyouga
f5962f8128 fix paligemma data preprocess
Former-commit-id: 71b85437301739d9d96d3881d4a34b37c0f69db8
2024-05-20 23:51:32 +08:00
hiyouga
b31d808655 fix paligemma inference
Former-commit-id: 46357b7a677e8ba2e0a7c9d4ec1974abd061569c
2024-05-20 23:36:43 +08:00
hiyouga
e30975e9a2 add kto to webui
Former-commit-id: 6c866f4dbd45e868860be8351d1a65c4e1a4e02b
2024-05-20 21:20:25 +08:00
zhangzc
de9f1583c2 fix conflict
Former-commit-id: 6922b23a748c2459147bf44b96d86daa89f2c96c
2024-05-20 17:10:01 +08:00
hiyouga
ab48653e63 fix chat engines
do not use pop(key, default) since api assigns None to dict values


Former-commit-id: 3ebbd0b55ea07de2897c27ca54eeab5c3b319419
2024-05-20 00:36:43 +08:00
hoshi-hiyouga
6d7a1e3f8f Merge pull request #3812 from ycjcl868/feat/chat-support-system-prompt
feat: cli chat support system_message
Former-commit-id: 96596990527403e910c81e95e38bf2638541cf31
2024-05-20 00:31:32 +08:00
hoshi-hiyouga
e093dad7cb Update vllm_engine.py
Former-commit-id: 0b8278bd21baf35d3f60c6ed24f110b391c92a47
2024-05-20 00:31:04 +08:00
hoshi-hiyouga
b103a121f0 Update hf_engine.py
Former-commit-id: ce8b902e538c69d89f207db8a43c85072cd70265
2024-05-20 00:30:45 +08:00