1536 Commits

Author SHA1 Message Date
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
hiyouga
9912b43fcc update readme
Former-commit-id: e2c7de1b5147801b301cfc5da0e2866273da18f5
2024-05-28 16:41:34 +08:00
hiyouga
5ac37555a4 update readme
Former-commit-id: 30ef8ee1e86136f38f105b67f70c417d20552f41
2024-05-28 16:19:56 +08:00
hiyouga
34bdc730a6 fix #3931
Former-commit-id: 47e0072416b545d9718af4fa266a83f747b9a4f7
2024-05-28 13:44:22 +08:00
MengqingCao
e45a9d70fc add Ascend npu doc and dependency
Former-commit-id: 803d9f142a294f8c1e0b4e2046c214b0857ccfd6
2024-05-28 01:33:54 +00:00
hoshi-hiyouga
232b36059c Merge pull request #3925 from Yimi81/feat-fix-yi-template
fix yi template

Former-commit-id: 6caee1eb868b9f7b00578c6608883e89aa232d17
2024-05-27 22:59:32 +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
eaf9cc2195 Merge branch 'hiyouga:main' into main
Former-commit-id: cc1b82bf49b060987392c455fdbfe125ad667ec5
2024-05-27 20:10:58 +08:00
hiyouga
4bd276f58f add llava 1k datasets
Former-commit-id: 345d3355752f4a4dc454696a39f1610fffbbf382
2024-05-27 19:57:33 +08:00
hiyouga
f8cf0d5e5d update dpo examples
Former-commit-id: 69e32a7cb6336ca9a953c379ec794818b3f169bd
2024-05-27 19:56:04 +08:00
BUAADreamer
79bc60db33 Merge branch 'hiyouga:main' into main
Former-commit-id: d89e1f8bf8bad1dd125b4de8fe6c0b2b16411cb5
2024-05-27 19:00:48 +08:00
BUAADreamer
dc7c54067e add only tune lm and mm_proj
Former-commit-id: ba12ca430ec527fbfe4cd1eace0adb5c7712146a
2024-05-27 19:00:15 +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
hoshi-hiyouga
1078611259 Merge pull request #3876 from dongdongqiang2018/main
added adapted to 910B image

Former-commit-id: 0708cc8a24589b9f22ad3df6685e57d1da0336f2
2024-05-24 01:54:30 +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
donggang
86dfdf956d adapted to 910B image
Former-commit-id: e095254808aace63a1be878620f683902f51cfb3
2024-05-23 09:48:22 +00:00
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
09e78272c2 Update README_zh.md
Former-commit-id: 34c4ba6bf9bb89170446fb396aa06ae44d251de0
2024-05-21 18:30:59 +08:00
hiyouga
cccce564bd update wechat
Former-commit-id: 6613349562194b48c5fc57aa68e620b8fa83fc0a
2024-05-21 18:22:32 +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
247cda4b68 fix #3818
Former-commit-id: 3f366e05a34be224f53c5bf8334e57ae5d316004
2024-05-20 21:43:19 +08:00
hiyouga
e30975e9a2 add kto to webui
Former-commit-id: 6c866f4dbd45e868860be8351d1a65c4e1a4e02b
2024-05-20 21:20:25 +08:00