1102 Commits

Author SHA1 Message Date
hzhaoy
4721d0b8ff add: support selecting saved configuration files and loading training parameters
Former-commit-id: b27c4cfcb367f7ab0b56da3ba238c4d9c29ff4e7
2024-06-04 10:33:43 +08:00
hoshi-hiyouga
9b6bdf9449 Merge pull request #3829 from seanzhang-zhichen/add_dataset_sample_num
Add dataset sample num

Former-commit-id: 483eb47e5d670e23fb713b942f6890b8259f4363
2024-05-30 00:25:45 +08:00
hoshi-hiyouga
7b83c550ab Update loader.py
Former-commit-id: ca5dd7c6c115a359e4b50e93f4ffcc9f2955ec2f
2024-05-30 00:20:20 +08:00
hoshi-hiyouga
9fc713da89 Update loader.py
Former-commit-id: f9a88b89ca8b8f9a0c5def03b154f9d67f558edf
2024-05-30 00:17:21 +08:00
hoshi-hiyouga
c0f11a280e Update loader.py
Former-commit-id: b55fb611c57be03fb38218c7da1d96f6848496ba
2024-05-30 00:12:12 +08:00
hoshi-hiyouga
69a51cacb1 Update parser.py
Former-commit-id: 51dd454337941801d0a66eaadb0da2e007e9573d
2024-05-30 00:05:20 +08:00
hiyouga
820404946e better llamaboard
* easily resume from checkpoint
* support full and freeze checkpoints
* faster ui


Former-commit-id: 80708717329b4552920dd4ce8cebc683e65d54c5
2024-05-29 23:55:38 +08:00
hiyouga
19a3262387 fix cohere system
Former-commit-id: d0aa36b8ad02287d97930101958456c523e699d3
2024-05-29 20:58:23 +08:00
hiyouga
c05cb3769f fix #3965
Former-commit-id: 0930f5869929634baa0881167d3d6c714afc63d9
2024-05-29 20:55:51 +08:00
hiyouga
a71a6a05c3 update readme
Former-commit-id: 89ca832740731dfb121175aa5c16b13bd4944011
2024-05-29 18:39:11 +08:00
hzhaoy
ce1be3da4b add TeleChat-12B/TeleChat-12B-v2 models
Former-commit-id: 0dd632fe9e5bbf08605d4b9c6887208b7a127317
2024-05-29 15:00:37 +08:00
hiyouga
05277ee864 fix hf chat engine
Former-commit-id: 97346c1d3d87f0bd5ddcd70ff485f6a8273244aa
2024-05-29 01:20:07 +08:00
hiyouga
13e7b64641 add ds config to webui
Former-commit-id: e4b420c146235b2bce70d66a081efd137aef98af
2024-05-29 01:13:17 +08:00
hiyouga
468d0e7ed1 10x generate in ppo w/ zero3
https://github.com/huggingface/trl/pull/1483

Former-commit-id: 65cd8bdbdbe1b19250ecd813aeb72c8e00ef2f9c
2024-05-29 00:23:23 +08:00
hiyouga
bfac965f9c update dpo, kto trainer
Former-commit-id: 7c8e01bb74bb2d2da5dba5059a9c262e4730b802
2024-05-29 00:14:29 +08:00
hiyouga
14f6cc2b7c clean kto trainer
Former-commit-id: 900e1ea622a2ffa45c5e2a359471962563fabca7
2024-05-28 21:43:26 +08:00
hiyouga
87e71df597 bump vllm version to 0.4.1
Former-commit-id: 1e80a3a6385f615bf038806b9c6b1f73f4a3e24f
2024-05-28 21:27:27 +08:00
hiyouga
3152c7dd1c update readme
Former-commit-id: 087b9faa3947bf6d2a53a8dedef487a662d426af
2024-05-28 19:35:52 +08:00
hiyouga
3ea8f5e6b9 support DDP in webui
Former-commit-id: 7c016b22aa9208ec14f00a9bdb51f69aebb02af5
2024-05-28 19:24:22 +08:00
Yimi81
7324984127 fix yi template
Former-commit-id: dc07413e7d0b138c89eacaef17596e83ef226540
2024-05-27 13:11:25 +00:00
hiyouga
0706dbf7e6 tiny fix
Former-commit-id: c1fdf81df6ade5da7be4eb66b715f0efd171d5aa
2024-05-27 20:54:26 +08:00
hoshi-hiyouga
ad3ca3f556 Merge pull request #3921 from gusye1234/main
Add openchat-3.6-8B support

Former-commit-id: 87ea0a8bcd8d76a9e916cc8da6905bc805bb18aa
2024-05-27 20:52:37 +08:00
hoshi-hiyouga
eceec1d7fd Update template.py
Former-commit-id: f1002b9f930758bb27794ab88a2adbe24417b076
2024-05-27 20:51:56 +08:00
hoshi-hiyouga
b7b8223230 Update template.py
Former-commit-id: 122213a7a7e114b0c390158cac0ae9faeceb2efc
2024-05-27 20:51:26 +08:00
Jianbai Ye
d2c1df7f3d add openchat-3.6-8B support
Former-commit-id: cff815391fd15f30647e8694e08c47a514fd6eb2
2024-05-27 20:42:08 +08:00
hiyouga
b88ecd71fd fix full/freeze tuning for mllm
Former-commit-id: 08564838bd02651668845ed74e2e60561e5b6d8c
2024-05-27 20:37:57 +08:00
hoshi-hiyouga
605e70d0e1 Merge pull request #3835 from BUAADreamer/main
fix some features in llava-style training

Former-commit-id: 838f2fb3e423a0471ff2898f737401e92bbafe2b
2024-05-27 20:23:45 +08:00
hiyouga
fc5a6b5c4e support Aya23
Former-commit-id: e626e264460d12b282099bfbb8e6679c31e85fc0
2024-05-27 20:23:24 +08:00
BUAADreamer
5632ba3fa8 Merge branch 'hiyouga:main' into main
Former-commit-id: ea2afd429eab85a67d562c3f7d571ede31320393
2024-05-27 19:00:48 +08:00
BUAADreamer
606240aec0 add regex of only tune lm and mm_proj
Former-commit-id: 57eb13b75d8597d748e84d3549a0b08876b669db
2024-05-27 18:59:00 +08:00
hiyouga
51a1097c64 add phi-3 7b/14b, mistral v0.3 models
Former-commit-id: efa4b196ca8053881bb9d15cfb571204bcb0bbda
2024-05-27 18:20:16 +08:00
hiyouga
df33548b39 update readme
Former-commit-id: 5581cb2e4e59f3f8109e2acd4611789f9e50bfca
2024-05-27 18:14:02 +08:00
BUAADreamer
a6c2a2071d Merge branch 'hiyouga:main' into main
Former-commit-id: 4bc7c10c00e6e9b5af8538af907178a37e3595f8
2024-05-27 11:54:01 +08:00
hiyouga
4807c11db8 support SimPO #3900
Former-commit-id: cb63b32986c43f97994211ec34dc5928fc3bb9d7
2024-05-26 23:46:33 +08:00
BUAADreamer
3eaf371a22 Merge branch 'hiyouga:main' into main
Former-commit-id: 60170a1da42a395cf440bbd3825c4e295c31ac38
2024-05-25 14:18:49 +08:00
hiyouga
e5d2ef4434 fix #3853
Former-commit-id: 063f91cc80193853d17c55fe092fb33683f5d39c
2024-05-24 23:29:45 +08:00
seanzhang-zhichen
9c8d79fbe3 Merge branch 'main' into add_dataset_sample_num
Former-commit-id: 27cb51f7f86f97ae231abfdcb0114ff245d7af9c
2024-05-24 15:57:47 +08:00
BUAADreamer
119af92620 Merge branch 'hiyouga:main' into main
Former-commit-id: 047a06a1e5336625acac14b3533ab3ef2b9905be
2024-05-24 09:50:00 +08:00
hiyouga
3e729798df refactor data preprocessing, fix mllm rlhf
Former-commit-id: 3a023bca2a502810a436cfba7708df164754ea62
2024-05-24 04:08:25 +08:00
hiyouga
d3490aceb7 fix paligemma sft
requires transformers>=4.41.1


Former-commit-id: de0e67aff13f191fd899ad717ec349a6bdb14f2a
2024-05-24 00:23:40 +08:00
hiyouga
6d8ef03741 fix oom issues in export
Former-commit-id: 67ebc7b388c61b9d880c02d7fd217c29299fdf43
2024-05-23 23:32:45 +08:00
BUAADreamer
d8a27e40e2 Merge branch 'hiyouga:main' into main
Former-commit-id: 8d53ec2b5f37e7b43da8d3e787f68fc1bb15997a
2024-05-21 22:18:20 +08:00
hiyouga
4ddc1c9c16 fix paligemma sft
Former-commit-id: 7134fb02bbdc9421f6c314ae176d5786a8cd768d
2024-05-21 20:03:09 +08:00
hiyouga
11f79ea20e fix #3847
Former-commit-id: 335501e228b7c2c2e3041533ddd996127b958f23
2024-05-21 17:53:06 +08:00
BUAADreamer
071d674065 support pretraining of llava
Former-commit-id: 29a6d5bdb8610be8f796eed65eede9ba7b503527
2024-05-21 08:57:14 +08:00
hiyouga
cce3892f91 support paligemma
Former-commit-id: 2a67457e3944d5e528286cb7203857c13078c484
2024-05-21 00:01:22 +08:00
hiyouga
a935c5105d fix paligemma data preprocess
Former-commit-id: e55c85ac72f4938738dbce576f83b47a1fea88ae
2024-05-20 23:51:32 +08:00
hiyouga
446c681b58 fix paligemma inference
Former-commit-id: 542229abb3aba2032d4c52a878c0fd35ba299691
2024-05-20 23:36:43 +08:00
hiyouga
5351e3945b add kto to webui
Former-commit-id: 9b0f4d7602f70031cc1a5fd66616cbe6bb4d78d3
2024-05-20 21:20:25 +08:00
zhangzc
4b90f04c1f fix conflict
Former-commit-id: d956041640d9abc5e59919a227d27270fb513a7e
2024-05-20 17:10:01 +08:00