2549 Commits

Author SHA1 Message Date
hiyouga
c89d17ab63 refactor mllm param logic
Former-commit-id: f6f630a1c96514053176abb12e35a06242e62abd
2025-01-10 15:45:48 +00:00
hoshi-hiyouga
b3561ae552 Merge pull request #6588 from hiyouga/hiyouga/upd_issue_temp
[gh] update issue template

Former-commit-id: 5ffd8ad192bb3932fbe230757d4bf1c907ca3aa4
2025-01-10 03:03:48 +08:00
hiyouga
b395540826 update issue template
Former-commit-id: aa8d0a223b0345e1f665b6703678c0ce526ff950
2025-01-09 18:58:53 +00:00
hoshi-hiyouga
a1b5644889 Merge pull request #6585 from hiyouga/hiyouga/add_phi4
[model] add phi4 model

Former-commit-id: 8b209cb49d9cc6058ce61c97bf2216f6371c5f7c
2025-01-10 02:39:17 +08:00
hiyouga
b471def13d improve template, add phi4 model
Former-commit-id: ae16ea755d581a5a288fb55f12481215f369b255
2025-01-09 18:27:54 +00:00
hoshi-hiyouga
b777fed171 Merge pull request #6564 from stephen-nju/fix_ray
Fix ray

Former-commit-id: 6b34b69fa688c4622489d3d5f33d847fb6b95528
2025-01-08 18:14:18 +08:00
hoshi-hiyouga
618ceda6e9 Merge pull request #6565 from hiyouga/hiyouga/improve_log
[misc] imporve log

Former-commit-id: 18431527bac8da57d9a2fc014695e5891f7a3068
2025-01-08 18:08:21 +08:00
zhubin
014a7ea042 fix –get ray args when args not a dict
Former-commit-id: 9c4c84828b77acf48caf60726e4e7ef3e972118d
2025-01-08 10:06:02 +00:00
hiyouga
da542fad18 imporve log
Former-commit-id: 47e17dd689840ca9b3c5f34448e5f80265336cca
2025-01-08 09:56:10 +00:00
hoshi-hiyouga
984b202f83 Merge pull request #6542 from erictang000/et/ray-integration
Ray Train integration with LLaMA-Factory

Former-commit-id: d23a98825bcb569bc51e21a3c2236eccd2f6d2fd
2025-01-08 11:46:03 +08:00
hiyouga
0c1ad5f3fb fix llamaboard with ray
Former-commit-id: c46675d5e56d175c27d705ef0068fb47dc89a872
2025-01-07 09:59:24 +00:00
hiyouga
b4174021d6 refactor ray integration, support save ckpt
Former-commit-id: d8cac6f54663e6cffeddf2c65e3da454e7b86a75
2025-01-07 09:39:10 +00:00
Eric Tang
bba52e258e run style check
Former-commit-id: 1e8e7be0a535e55888f58bbe2c38bc1c382e9012
2025-01-07 08:55:44 +00:00
Kourosh Hakhamaneshi
1217240918 drafting ray integration
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>

Former-commit-id: 163ddb680b6f84a4424a887a3b8a5d668044e87c
2025-01-07 08:55:44 +00:00
hoshi-hiyouga
a0bcac80c0 Merge pull request #6547 from hiyouga/hiyouga/fix_pixtral_dpo
[trainer] fix pixtral dpo

Former-commit-id: c973f32849b979a3ebb80caa01029b43fbb620ac
2025-01-07 14:38:55 +08:00
hiyouga
8c57169eb7 fix #6546
Former-commit-id: 870f23d7eaff1e32a73fee4eb972163c85ba7b67
2025-01-07 06:30:44 +00:00
hoshi-hiyouga
621d73e87c Merge pull request #6528 from hiyouga/hiyouga/upd_wechat
[assets] update wechat

Former-commit-id: b832ed9a60a5fd0bc7d9f975bb881a71e7d35245
2025-01-04 16:01:21 +08:00
hiyouga
a02a140840 update wechat
Former-commit-id: cd1433650653810f7934c65cb1de91052eb73dcf
2025-01-04 07:59:57 +00:00
hoshi-hiyouga
084d356c2c Merge pull request #6524 from hiyouga/hiyouga/upd_scripts
[misc] update scripts

Former-commit-id: e6d603ac374c04df354361f9617173afa8c1edae
2025-01-03 23:52:26 +08:00
hiyouga
20a9565e36 update scripts
Former-commit-id: dd44c65d7f60cb6f5d0e0d8ee5f4e7643defb89b
2025-01-03 10:50:32 +00:00
hoshi-hiyouga
85317bcbaf Merge pull request #6515 from hiyouga/hiyouga/misc
[misc] update model name

Former-commit-id: 51ef90ce0ace4a45f9c01ba7e674adf5e3c92baa
2025-01-02 20:20:02 +08:00
hiyouga
528fb4f799 update model name
Former-commit-id: 4b8add728729d8e2ce4c9a3dc6748357291d8e8b
2025-01-02 12:19:21 +00:00
hoshi-hiyouga
aa7ec44367 Merge pull request #6514 from hiyouga/hiyouga/add_project
[readme] add project

Former-commit-id: a766cad5d49f226eb61a550bc3d157870c1068cc
2025-01-02 20:16:15 +08:00
hoshi-hiyouga
b2ecb80729 Merge pull request #6513 from hiyouga/hiyouga/add_gpt2
[model] add gpt2 model

Former-commit-id: 29ddc6b77862f740570a00d3b8ea548ee1a2ce03
2025-01-02 20:15:55 +08:00
hiyouga
9a3afbd5d1 add project
Former-commit-id: b3e1137fbbdfa4cc081903983fea36acff7afd75
2025-01-02 12:15:41 +00:00
hiyouga
37c60c7d14 add gpt2 model
Former-commit-id: 67442bd497c75b0c5990d94a880e0e25474ae2fa
2025-01-02 12:07:38 +00:00
hoshi-hiyouga
b921dde749 Merge pull request #6512 from hiyouga/hiyouga/fix_gen_logic
[trainer] fix generate logic

Former-commit-id: 72d86ecc9e327933a0a2c893b8ffd2740c99be6b
2025-01-02 19:36:54 +08:00
hoshi-hiyouga
d195329185 Merge pull request #6462 from shibingli/main
Add ARG HTTP_PROXY in Dockerfile to support HTTP proxy during image building

Former-commit-id: 8741e5b3e87a392a3c9d50455e4916c3a938fb24
2025-01-02 19:34:17 +08:00
hiyouga
da8721a70e fix #6499
Former-commit-id: 1800f8c72dfa618c71c84a3a18ecdef4d82754f7
2025-01-02 11:28:54 +00:00
hoshi-hiyouga
f318dc9464 Merge pull request #6493 from hiyouga/hiyouga/upd_wechat
[assets] update wechat

Former-commit-id: f8e80d566f7666b6af00360df97065698a1d3a9f
2024-12-30 21:55:03 +08:00
hiyouga
01bbe66f41 update wechat
Former-commit-id: a400d896a18e317acdbd3c79282c81b50cc2c54d
2024-12-30 13:54:22 +00:00
hoshi-hiyouga
bb664d2fc5 Merge pull request #6492 from hiyouga/hiyouga/add_deepseek3
[model] add deepseek3 model

Former-commit-id: 2382a5f0317d768ba8f4931977f5caed6057b3c0
2024-12-30 21:50:13 +08:00
hiyouga
d0e729cd33 add deepseek3 model
Former-commit-id: e67b9dcc3ad0c003bc3afd7601ecd2adfbf9666b
2024-12-30 13:39:20 +00:00
hoshi-hiyouga
1178cb0e33 Merge pull request #5507 from piamo/main
Add deepseek-v2.5 template

Former-commit-id: 91467ed313802ac3950c2e11a7d0997a36bcbddd
2024-12-30 21:08:25 +08:00
hoshi-hiyouga
089f824cd1 Merge pull request #6483 from hiyouga/hiyouga/fix_paligemma_infer
[model] update vllm & fix paligemma dtype

Former-commit-id: 40805b0cc0cff478703f68067a330ba307bb5809
2024-12-30 16:34:32 +08:00
hiyouga
813f5919a3 fix #6482
Former-commit-id: 6f5bb3b8e5b6eb7fdfd7b0ca8eba789ab741a7b6
2024-12-30 06:03:07 +00:00
hoshi-hiyouga
951d845af2 Merge pull request #6465 from hiyouga/hiyouga/fix_eval_loss
[trainer] fix eval loss

Former-commit-id: b55890291b0049dd90ef4d1d0bf0ba1efb1e4f0a
2024-12-28 01:02:56 +08:00
hiyouga
3bcb4633ca fix #6448
Former-commit-id: 27198679829fb766c7eef468ae4311fdced695a2
2024-12-27 16:54:39 +00:00
shibingli@yeah.net
c76c33ddb1 Add ARG HTTP_PROXY in Dockerfile to support HTTP proxy during image building.
Former-commit-id: f1d76786e094562f6f095a0b56c9c6cd32e2fa5e
2024-12-27 18:31:14 +08:00
shibingli@yeah.net
a37ef0eaae Add ARG HTTP_PROXY in Dockerfile to support HTTP proxy during image building.This commit introduces an ARG parameter named HTTP_PROXY in the Dockerfile. This addition allows for the configuration of an HTTP proxy, facilitating image building in environments with network restrictions.
Former-commit-id: a3a49b1ea477313c979a1649ee6a7f843fe36469
2024-12-27 18:17:17 +08:00
hoshi-hiyouga
377dfe5665 Merge pull request #6457 from youkaichao/module-run
[misc] enable module run

Former-commit-id: f68074d87bcc915a49a8765b3ebb32d935aa5445
2024-12-26 23:41:37 +08:00
youkaichao
f6d5dd6f10 Update cli.py
Former-commit-id: c39d81cd1d108d832746e100ac890b2d4ecaa60e
2024-12-26 23:22:09 +08:00
hoshi-hiyouga
a36f9d923e Merge pull request #6443 from hiyouga/hiyouga/add_qvq
[modle] add qvq

Former-commit-id: cd56f88ff2c5c3edc381f3807f466621cee86b67
2024-12-25 15:53:19 +08:00
hiyouga
c83b74ab9e add qvq #6439
Former-commit-id: ee0e400f417f648cd15cf48144df76e4809cc615
2024-12-25 07:52:41 +00:00
hoshi-hiyouga
c5780f5eaa Merge pull request #6430 from hiyouga/hiyouga/upd_wechat
[assets] update wechat

Former-commit-id: cbd494ddaf692faf83d4825fe4b4595430b111f5
2024-12-24 16:13:20 +08:00
hiyouga
4cd1d05429 update wechat
Former-commit-id: 83202c9027222b83c949d1fe1bff1317f5715015
2024-12-24 08:12:53 +00:00
hoshi-hiyouga
459219a260 Merge pull request #6426 from hiyouga/hiyouga/update_readme
[assets] update readme

Former-commit-id: b9f73fc5caf5753bd5b96de5383eaf80cd958e3d
2024-12-23 22:17:19 +08:00
hiyouga
353259f03f update readme
Former-commit-id: 8fd38d273e5bc3b28a4741b230010fece87e7070
2024-12-23 14:08:59 +00:00
hoshi-hiyouga
8265d6a228 Merge pull request #5922 from Tuyohai/main
support granite3 models

Former-commit-id: c23a4d0658323434c386716c25855711202e37a9
2024-12-23 16:46:02 +08:00
hoshi-hiyouga
c0418062c0 Merge pull request #6418 from hiyouga/hiyouga/add_report
[trainer] add custom args to experimental logger

Former-commit-id: d58746eca203d97ec57abbc312ecf4c00b5d5535
2024-12-22 05:47:55 +08:00