2771 Commits

Author SHA1 Message Date
hiyouga
b948bb540e update issue template
Former-commit-id: 2bfca993588d8087dfd118f6f02486bbe752b166
2025-01-09 18:58:53 +00:00
hoshi-hiyouga
2874b590be Merge pull request #6585 from hiyouga/hiyouga/add_phi4
[model] add phi4 model

Former-commit-id: 0ae6a9b7bf9f1d6d844b97406b4795363bf75e78
2025-01-10 02:39:17 +08:00
hiyouga
edba9b534f improve template, add phi4 model
Former-commit-id: a785b6796e445a3adba45c5b6947166a2ff99871
2025-01-09 18:27:54 +00:00
hoshi-hiyouga
9ce3cbf3c7 Merge pull request #6564 from stephen-nju/fix_ray
Fix ray

Former-commit-id: d4566839369726023f1b6e8f4b2332bda0c715cc
2025-01-08 18:14:18 +08:00
hoshi-hiyouga
f79e4033af Merge pull request #6565 from hiyouga/hiyouga/improve_log
[misc] imporve log

Former-commit-id: 538bf7b839c63d6a6758522fa08999d9b78e9db2
2025-01-08 18:08:21 +08:00
zhubin
b0fb054637 fix –get ray args when args not a dict
Former-commit-id: 5e5398cd5b117b2378107172d3f91cfb0321e842
2025-01-08 10:06:02 +00:00
hiyouga
760dea0787 imporve log
Former-commit-id: a6abf375975ffea3d51e1b944c9855b5f62ffac8
2025-01-08 09:56:10 +00:00
hoshi-hiyouga
da931e73c8 Merge pull request #6542 from erictang000/et/ray-integration
Ray Train integration with LLaMA-Factory

Former-commit-id: 4e34ee0a8e0aa90b535e53608b51c5c0804db34e
2025-01-08 11:46:03 +08:00
hiyouga
bd61102b5e fix llamaboard with ray
Former-commit-id: bd8a432d6a980b1b24a551626304fe3d394b1baf
2025-01-07 09:59:24 +00:00
hiyouga
708e899769 refactor ray integration, support save ckpt
Former-commit-id: 2f50b27e608b2092bfceab6c6e84e6631e973ee2
2025-01-07 09:39:10 +00:00
Eric Tang
88e9badcbb run style check
Former-commit-id: 5ec33baf5f95df9fa2afe5523c825d3eda8a076b
2025-01-07 08:55:44 +00:00
Kourosh Hakhamaneshi
09a17b5415 drafting ray integration
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>

Former-commit-id: 19c12ddae9350f6e25a270fe3372f5b9094cf960
2025-01-07 08:55:44 +00:00
hoshi-hiyouga
e258f1da98 Merge pull request #6547 from hiyouga/hiyouga/fix_pixtral_dpo
[trainer] fix pixtral dpo

Former-commit-id: 920bb2a8922847fa544e2c260c67161e64cf5d50
2025-01-07 14:38:55 +08:00
hiyouga
8d1b77cd6f fix #6546
Former-commit-id: 6fcf2f10faf3b1614896b091591eeef96d717e64
2025-01-07 06:30:44 +00:00
fzc8578
19fbac1902 add some
Former-commit-id: b4790c66c126567bd193de52a564e3ce11c94769
2025-01-06 19:32:39 +08:00
hoshi-hiyouga
495ff0175e Merge pull request #6528 from hiyouga/hiyouga/upd_wechat
[assets] update wechat

Former-commit-id: 3ceedf44896b5ebc406d6398b3f15e74e4710fbe
2025-01-04 16:01:21 +08:00
hiyouga
675fa692e6 update wechat
Former-commit-id: 11a9d96a042e8afd972e0bf2fa3e51f95e4799ec
2025-01-04 07:59:57 +00:00
Zhangchi Feng
ba1d3fd81f Merge branch 'hiyouga:main' into minicpmv
Former-commit-id: 873b2d5888038e2328a12a6eb7c84099ba7ca1f3
2025-01-04 11:20:33 +08:00
fzc8578
8f97891153 add some
Former-commit-id: 81176fe226da89eace89cb202bad68e73b7c2a02
2025-01-04 11:11:15 +08:00
hoshi-hiyouga
efc4a41bc2 Merge pull request #6524 from hiyouga/hiyouga/upd_scripts
[misc] update scripts

Former-commit-id: 6ba3ec45fc369c095ab9a1fbd9847dc66cf24ca4
2025-01-03 23:52:26 +08:00
hiyouga
074c9db3a6 update scripts
Former-commit-id: 05aa52adde8905ca892f1ed5847d6f90b1992848
2025-01-03 10:50:32 +00:00
hoshi-hiyouga
f1a7e5c483 Merge pull request #6515 from hiyouga/hiyouga/misc
[misc] update model name

Former-commit-id: f92eea4090351dcd3c364e10a9eec0d17d480e12
2025-01-02 20:20:02 +08:00
hiyouga
9ef54d5f3c update model name
Former-commit-id: bf627d9f1ac117f040adbfd7630b5283f0db556a
2025-01-02 12:19:21 +00:00
hoshi-hiyouga
945f27a951 Merge pull request #6514 from hiyouga/hiyouga/add_project
[readme] add project

Former-commit-id: 0bd0c373183731302f1af9f33a1f8ff70ba743e2
2025-01-02 20:16:15 +08:00
hoshi-hiyouga
f1e470d42e Merge pull request #6513 from hiyouga/hiyouga/add_gpt2
[model] add gpt2 model

Former-commit-id: 859c37f43c8a49eea4f118d0d00ee2a554f6bd4f
2025-01-02 20:15:55 +08:00
hiyouga
816f0c7680 add project
Former-commit-id: 3b7e745d271e36b4cfe8826820b23254e1debfe9
2025-01-02 12:15:41 +00:00
hiyouga
36fc0e9a4d add gpt2 model
Former-commit-id: 37d5e3639fcf5ae6e58cc435e0fa9dee0d6e4ead
2025-01-02 12:07:38 +00:00
hoshi-hiyouga
c09c362206 Merge pull request #6512 from hiyouga/hiyouga/fix_gen_logic
[trainer] fix generate logic

Former-commit-id: b97759421c535560ade631a7fa0a57b7c0da50f1
2025-01-02 19:36:54 +08:00
hoshi-hiyouga
df281c459e Merge pull request #6462 from shibingli/main
Add ARG HTTP_PROXY in Dockerfile to support HTTP proxy during image building

Former-commit-id: 1e72bb24253bb07da874f3a37ccfa4fddaaf6978
2025-01-02 19:34:17 +08:00
hiyouga
9e7a7c5651 fix #6499
Former-commit-id: dffc607220ff6dac15cf501ac9a3cdbe80c25211
2025-01-02 11:28:54 +00:00
hoshi-hiyouga
9189f16aa7 Merge pull request #6492 from hiyouga/hiyouga/add_deepseek3
[model] add deepseek3 model

Former-commit-id: 0a6d1244a51f3cc8fe141b32f39bffce4c924a8c
2024-12-30 21:50:13 +08:00
hiyouga
0b20167b61 add deepseek3 model
Former-commit-id: 611779d412f31e25b1ed38049050eee2da61dde5
2024-12-30 13:39:20 +00:00
hoshi-hiyouga
68e11c59fd Merge pull request #5507 from piamo/main
Add deepseek-v2.5 template

Former-commit-id: 8a4911d201e219465fe0835a3ceb967f8b80dc0e
2024-12-30 21:08:25 +08:00
hoshi-hiyouga
df09c5d109 Merge pull request #6483 from hiyouga/hiyouga/fix_paligemma_infer
[model] update vllm & fix paligemma dtype

Former-commit-id: 03ad6d44805a965764aaa51376964972b9b7da3d
2024-12-30 16:34:32 +08:00
hiyouga
92c6c384cf fix #6482
Former-commit-id: 8577f52b4152efe6cc7a8b5f6d37b4f9ba6684e7
2024-12-30 06:03:07 +00:00
hoshi-hiyouga
f405c47191 Merge pull request #6465 from hiyouga/hiyouga/fix_eval_loss
[trainer] fix eval loss

Former-commit-id: fa8110b2052a74b4bd0dcf391a54207e1e31056d
2024-12-28 01:02:56 +08:00
hiyouga
c555a83ec9 fix #6448
Former-commit-id: 04f78e85af5af14b4c195936623e426a6a128af2
2024-12-27 16:54:39 +00:00
shibingli@yeah.net
928dc1cb83 Add ARG HTTP_PROXY in Dockerfile to support HTTP proxy during image building.
Former-commit-id: c46af4c45f96f1942dfaf77bdbdbe5d0fe85a387
2024-12-27 18:31:14 +08:00
shibingli@yeah.net
31424e4f77 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: d59fe30bca636bc2ca132d50172dba0032cecb6b
2024-12-27 18:17:17 +08:00
hoshi-hiyouga
6ccb21276e Merge pull request #6457 from youkaichao/module-run
[misc] enable module run

Former-commit-id: 813881a5d13dd1d5a526a85d41032196e0d46f04
2024-12-26 23:41:37 +08:00
youkaichao
ee4682ba0e Update cli.py
Former-commit-id: 18e65bbd3ae07af3b9eed7f293c345815776c325
2024-12-26 23:22:09 +08:00
hoshi-hiyouga
9c76fb960d Merge pull request #6443 from hiyouga/hiyouga/add_qvq
[modle] add qvq

Former-commit-id: 2010e80b1a939d21efa13d54df5f5d648ea640de
2024-12-25 15:53:19 +08:00
hiyouga
6891d468a0 add qvq #6439
Former-commit-id: 4dbfa142d899dd6e4d1a9d4db125765af5580a4f
2024-12-25 07:52:41 +00:00
hoshi-hiyouga
32c6c27464 Merge pull request #6426 from hiyouga/hiyouga/update_readme
[assets] update readme

Former-commit-id: 2309c431090d1f3b573d113bbedeabee2b01fdf2
2024-12-23 22:17:19 +08:00
hiyouga
a64d93ed28 update readme
Former-commit-id: 1deda4750e0df6c46aeb33cf3f8b35baa537cc1d
2024-12-23 14:08:59 +00:00
hoshi-hiyouga
3f842b4cd0 Merge pull request #5922 from Tuyohai/main
support granite3 models

Former-commit-id: a9087bc0549f7f16e5b4c39e324043755b1618c8
2024-12-23 16:46:02 +08:00
hoshi-hiyouga
cd3bf6d546 Merge pull request #6418 from hiyouga/hiyouga/add_report
[trainer] add custom args to experimental logger

Former-commit-id: 5e5a7ba73c1a386f025d75c10b102306bcb98674
2024-12-22 05:47:55 +08:00
hiyouga
c57fbebd55 support report custom args
Former-commit-id: d41254c40a1c5cacf9377096adb27efa9bdb79ea
2024-12-21 21:42:45 +00:00
hiyouga
2baa6ec83c fix paligemma infer
Former-commit-id: d272455d6118c1d670c70cfe3458d8dab111da6c
2024-12-21 20:24:32 +00:00
hoshi-hiyouga
79d8a6bdb7 Merge pull request #6416 from Zeyi-Lin/main
docs: use swanlab
Former-commit-id: 0759b576a36cde120ccb8cadd96fca4d871be130
2024-12-22 04:08:26 +08:00