Commit Graph

352 Commits (fe7fc29435d05bb256de19c87a27d157511a9997)

Author SHA1 Message Date
jingyaogong ecd1ae1563 [fix] reduce aux_loss_alpha 2025-12-05 23:08:29 +08:00
jingyaogong 5e1447b913 [fix] cuda memory #559 2025-12-01 16:17:43 +08:00
jingyaogong 151fdf7e76 [feat] update yarn 2025-12-01 16:15:05 +08:00
jingyaogong 6b86ea399a [feat] release memory 2025-11-27 19:39:49 +08:00
yuyu5333 0ebf835006 update start bash 2025-11-25 03:44:53 +00:00
yuyu5333 aee1913d3d update para from_resume 2025-11-25 03:28:56 +00:00
wangyuzhan d9dddccd71 update process step 2025-11-21 18:43:41 +08:00
wangyuzhan 826a1fbe1e add process step 2025-11-21 17:44:24 +08:00
yuyu5333 b336bc6008 remove useless file 2025-11-21 17:22:33 +08:00
yuyu5333 5e5b1bedb0 update web ui 2025-11-21 15:34:01 +08:00
wangyuzhan 80f75a252b update log flash 2025-11-21 15:11:11 +08:00
wangyuzhan dfe1e5c6c7 update web dataset file 2025-11-21 14:11:37 +08:00
wangyuzhan 8845d9170c update web dataset file 2025-11-21 12:33:04 +08:00
wangyuzhan 249d1c08fe update web dataset file 2025-11-21 12:09:05 +08:00
wangyuzhan a0013eae8f update web dataset file 2025-11-21 10:41:05 +08:00
wangyuzhan 4a741b3d3b update web dataset file 2025-11-20 21:55:48 +08:00
wangyuzhan fc1f07bf74 remove sdk 2025-11-20 21:19:28 +08:00
wangyuzhan 102a7c0199 update web ui 2025-11-20 20:47:00 +08:00
wangyuzhan a95568644b update import web 2025-11-20 17:21:10 +08:00
wangyuzhan a794898a18 update check web server health 2025-11-20 15:58:31 +08:00
wangyuzhan 25cf74eec1 update sdk 2025-11-20 15:54:08 +08:00
jingyaogong d7f4f4eab8 [fix] ppo mask 2025-11-19 23:39:02 +08:00
jingyaogong f5374dc87f [fix] model attn_mask 2025-11-19 22:26:53 +08:00
wangyuzhan 66dcb40db7 init sdk 2025-11-18 21:35:26 +08:00
wangyuzhan 52b7b88ec2 update web 2025-11-18 21:21:13 +08:00
jingyaogong a044578d73 [fix] update model 2025-11-18 13:07:20 +08:00
jingyaogong ce9394670b
Merge pull request #536 from yuyu5333/fix/attn_forward
fix: attn_forwad when is_causal=True assert attn_mask is None
2025-11-18 13:02:46 +08:00
yuyu5333 7d02ce673c fix: attn_forwad when is_causal=True assert attn_mask is None 2025-11-18 03:17:17 +00:00
yuyu5333 49bd32f168 support rl-grpo, rl-spo 2025-11-17 17:46:19 +08:00
jingyaogong 9c98cabc9a [fix] prompt length calculate 2025-11-15 18:25:37 +08:00
yuyu5333 544c889533 rewrite web 2025-11-14 16:08:30 +08:00
yuyu5333 ebf1a853ab update bash start 2025-11-14 15:45:36 +08:00
wangyuzhan c0b39e2396 rewrite web 2025-11-14 14:21:14 +08:00
yuyu5333 7c947e59c1 update http && process logs 2025-11-13 07:01:05 +00:00
yuyu5333 3a03cedd00 support Swanlab check 2025-11-11 13:26:34 +00:00
yuyu5333 04477b72f2 update safe web 2025-11-11 07:43:17 +00:00
yuyu5333 d66a7945db support ppo and Training web code refactoring 2025-11-11 07:40:38 +00:00
jingyaogong f3441b0078
Merge pull request #528 from wangzhaode/feat/add_mnn_support
[feat] add MNN support to README.
2025-11-10 22:46:15 +08:00
yanxing 5959396096 [feat] add MNN support to README. 2025-11-10 21:59:22 +08:00
yuyu5333 237744d58a Merge remote-tracking branch 'upstream/master' into feat/as_a_tools 2025-11-10 11:08:05 +00:00
yuyu5333 095a656cff support ddp 2025-11-10 10:00:44 +00:00
yuyu5333 768f0708e3 add default model para 2025-11-10 07:29:20 +00:00
yuyu5333 9b27e8b716 update web auto port 2025-11-10 14:55:23 +08:00
jingyaogong bf60bde8fb [fix] model-name 2025-11-07 19:38:20 +08:00
yuyu5333 48a81d99bb update logfile && process 2025-11-07 09:34:19 +00:00
yuyu5333 5bef3f08ab add: rl-dpo 2025-11-07 05:13:13 +00:00
yuyu5333 e9d2ccbb2d fix training logs show 2025-11-07 03:11:22 +00:00
yuyu5333 9bfb58ad1e Init Web UI 2025-11-06 22:34:22 +08:00
jingyaogong 81e869fc3e [fix] harmonize template 2025-11-06 13:14:08 +08:00
jingyaogong 509d8dacf1 [feat] clear cache 2025-11-06 13:12:28 +08:00