louis_lifu
/
AReaL
mirror of https://github.com/inclusionAI/AReaL
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
293 Commits 12 Branches 4 Tags 21 MiB
Commit Graph

293 Commits

Author SHA1 Message Date
garrett4wade 9a06675ba0 . 2025-07-07 09:38:37 +08:00
Zijian Zhang 078d3e1a44
Add CI for testing AReaLite (#150) 
* ci: add test-arealite

* ci: add checkout before running test-arealite

* ci: add USERNAME

* ci: add test script

* ci: add GitHub mirror

* ci: fix typo

* ci: clone one commit

* ci: fix condition

* ci: set command timeout to 60m

* ci: enable pip cache

* ci: optimize container lifecycle

* ci: split into many stages

* ci(test-arealite): fix typo

* ci: fix wrong env

* ci: fix pytest

* ci: uninstall transformer-engine

* ci: uninstall transformer-engine

* ci: fix model paths

* ci: show stdout/stderr

* ci: fix not clean up

* ci: backup sglang

* ci: remove tmp repo dir when run

* ci: fix docker run exit 1 condition

* ci(test-arealite): limit the concurrency and extend command timeout
 2025-07-07 09:36:12 +08:00
bowei.fw 89a8d8c46a . 2025-07-04 16:28:32 +08:00
bowei.fw 3a8796b93a . 2025-07-02 11:28:20 +08:00
bowei.fw a5299b1bed . 2025-07-02 11:28:03 +08:00
bowei.fw ab7503af93 . 2025-07-02 10:07:40 +08:00
博惟 d1f863caf6 Merge branch 'fw/refactor2' of https://code.alipay.com/inclusionAI/AReaL into fw/refactor 2025-07-01 10:15:53 +08:00
博惟 df5ee49765 Merge branch 'fw/refactor' of https://github.com/inclusionAI/AReaL into fw/refactor 2025-07-01 10:14:24 +08:00
nuzant 09f339f7aa
Fix unresolved issue in SFTTrainer PR (#139) 
* .

* .

* efficient loading

* format

* .

* .
 2025-07-01 10:13:05 +08:00
bowei.fw 2ce1ecef3b . 2025-07-01 10:11:39 +08:00
bowei.fw c66ed17f40 . 2025-06-30 14:13:39 +08:00
bowei.fw 91d6399691 . 2025-06-30 13:29:41 +08:00
bowei.fw 86129327bb fix tests 2025-06-30 11:04:52 +08:00
garrett4wade a2ade35a9b . 2025-06-30 10:39:06 +08:00
bowei.fw d2a317d1fc refactor config structure 2025-06-28 11:23:22 +08:00
bowei.fw b424176b44 fix llm server api 2025-06-27 17:42:28 +08:00
garrett4wade 4320da83b5 . 2025-06-27 17:29:03 +08:00
bowei.fw 73b5b3e97e . 2025-06-27 16:22:03 +08:00
bowei.fw 77a557cc43 refactor llm_client location 2025-06-27 12:52:07 +08:00
bowei.fw 9724c8ac80 rename workflow to collector 2025-06-27 10:46:38 +08:00
博惟 8c338e99b0 Merge branch 'fw/refactor' of https://code.alipay.com/inclusionAI/AReaL into mzy/gh/sft 2025-06-26 21:54:23 +08:00
bowei.fw 15537cb013 . 2025-06-26 21:50:03 +08:00
meizhiyu.mzy f099bbd0a5 chmod fix 2025-06-26 19:44:09 +08:00
root 84ff7597da format 2025-06-26 19:36:59 +08:00
root 6ec4493cb1 . 2025-06-26 19:34:25 +08:00
bowei.fw 05a2df06a9 . 2025-06-26 14:39:00 +08:00
bowei.fw 7e7240d1d2 . 2025-06-26 14:23:00 +08:00
bowei.fw 63cd942995 add dataset api 2025-06-26 14:22:39 +08:00
bowei.fw eb431c11e0 reorganize code 2025-06-26 13:41:18 +08:00
bowei.fw 1be260ea6a change reward function organization 2025-06-26 13:36:44 +08:00
bowei.fw 59d288b834 rename ppo to grpo 2025-06-26 11:18:20 +08:00
bowei.fw 3059640cd0 clear unused imports 2025-06-26 10:58:04 +08:00
bowei.fw 242243b6a6 pass ppo and rollout controller tests 2025-06-26 10:55:07 +08:00
bowei.fw d07f595225 pass ppo unittest 2025-06-25 22:59:55 +08:00
garrett4wade aa8f4eff9b . 2025-06-25 20:50:38 +08:00
bowei.fw f9643b7512 . 2025-06-25 19:40:45 +08:00
bowei.fw 80193359a5 merge 2025-06-25 18:17:46 +08:00
garrett4wade 9b8306c28c . 2025-06-25 17:05:19 +08:00
meizhiyu.mzy 92e3a3db17 add fsdp engine and sft tests 2025-06-25 12:26:46 +08:00
meizhiyu.mzy ccdf0370d2 fix 2025-06-24 20:39:05 +08:00
晓雷 e7163ea385 merge fw/refactor 2025-06-24 20:18:57 +08:00
meizhiyu.mzy 5d5ac7830a . 2025-06-24 20:10:05 +08:00
garrett4wade 49a31c475d refine hf engine 2025-06-24 19:26:44 +08:00
meizhiyu.mzy b112d83487 . 2025-06-24 19:05:53 +08:00
meizhiyu.mzy 06060cf28c format 2025-06-24 19:04:09 +08:00
garrett4wade 8d2bd4e1a4 format 2025-06-24 10:12:48 +08:00
Jayon02 b4766bd711
add hf engine wrapper (#116) 
* add hf engine

* fix issues

* fix ppo bugs and add test

* add hf client interface and modify cli args

* fix bugs

* fix issues

* Merge fw/refactor

* Finish hf wrapper test

* add test

---------

Co-authored-by: Wei Fu <36355462+garrett4wade@users.noreply.github.com>
 2025-06-24 10:03:27 +08:00
garrett4wade 7695179adb remove unsed args in ppo 2025-06-23 21:40:16 +08:00
garrett4wade 6ed10c9a81 remove unused files 2025-06-23 20:33:52 +08:00
garrett4wade 302e876edd add lisence 2025-06-23 20:29:36 +08:00