jingyaogong
|
6534447b62
|
[fix] issue#771
|
2026-05-19 17:40:03 +08:00 |
jingyaogong
|
e90f92d701
|
[update] requirements
|
2026-05-16 18:08:37 +08:00 |
jingyaogong
|
4b0993fcc2
|
[fix] repetition_penalty
|
2026-05-07 19:08:52 +08:00 |
jingyaogong
|
a22f1f1486
|
[feat] reduce RL memory
|
2026-05-06 15:07:28 +08:00 |
jingyaogong
|
ed7cbcee19
|
Merge pull request #759 from TKiteRunner/fix/grpo-oom-reorder-rewards
fix: resolve CUDA OOM in train_grpo.py on GPUs with <=8GB VRAM
|
2026-05-06 15:00:17 +08:00 |
TKiteRunner
|
1c583deb28
|
fix: resolve CUDA OOM in train_grpo.py on GPUs with <=8GB VRAM
|
2026-05-06 14:14:15 +08:00 |
jingyaogong
|
43eee6add5
|
[update] readme
|
2026-05-06 13:41:46 +08:00 |
jingyaogong
|
58959684c7
|
[fix] inference bug
|
2026-05-03 20:48:48 +08:00 |
jingyaogong
|
d1148341bb
|
[update] readme
|
2026-05-01 12:06:47 +08:00 |
jingyaogong
|
7b4f029ee3
|
[update] readme
|
2026-04-28 17:22:25 +08:00 |
jingyaogong
|
4b85ba8b28
|
[fix] bugs
|
2026-04-27 19:16:08 +08:00 |
jingyaogong
|
3b7a4d04a2
|
[fix] rollout bugs
|
2026-04-27 17:54:09 +08:00 |
jingyaogong
|
b45c36b8b5
|
[update] readme
|
2026-04-27 10:59:41 +08:00 |
jingyaogong
|
e4e9153a1f
|
[update] readme
|
2026-04-24 20:16:06 +08:00 |
jingyaogong
|
29c87cfc8d
|
[update] readme
|
2026-04-24 20:14:10 +08:00 |
jingyaogong
|
c0eb98393f
|
[update] readme
|
2026-04-21 14:34:46 +08:00 |
jingyaogong
|
568a863520
|
[fix] bugs
|
2026-04-21 13:03:34 +08:00 |
jingyaogong
|
761710654a
|
[fix] transformers-5.x
|
2026-04-19 23:48:54 +08:00 |
jingyaogong
|
145a7ac6f6
|
[update] tie embedding
|
2026-04-19 21:57:28 +08:00 |
jingyaogong
|
83b4c697a3
|
[update] readme
|
2026-04-19 14:51:47 +08:00 |
jingyaogong
|
b9a229e1ae
|
[update] readme
|
2026-04-10 10:55:24 +08:00 |
jingyaogong
|
e612cc26e8
|
[fix] lora compile
|
2026-04-10 00:01:21 +08:00 |
jingyaogong
|
903eb1dd37
|
[update] readme
|
2026-04-09 19:00:41 +08:00 |
jingyaogong
|
6b9588d619
|
[update] readme
|
2026-04-09 18:54:17 +08:00 |
jingyaogong
|
d942f24bf1
|
[update] bench
|
2026-04-09 17:12:48 +08:00 |
jingyaogong
|
862dd151f2
|
[fix] lora moe
|
2026-04-09 16:36:48 +08:00 |
jingyaogong
|
b703844a60
|
[update] add a comment
|
2026-04-09 15:09:58 +08:00 |
jingyaogong
|
428f017e21
|
[update] image
|
2026-04-04 14:54:13 +08:00 |
jingyaogong
|
ef1c130a03
|
[update] readme
|
2026-04-04 11:25:21 +08:00 |
jingyaogong
|
7546729893
|
[update] open causal
|
2026-04-02 15:28:58 +08:00 |
jingyaogong
|
6512d5647a
|
[update] readme
|
2026-04-02 15:28:29 +08:00 |
jingyaogong
|
ea57409fd2
|
[update] readme
|
2026-04-01 14:00:21 +08:00 |
jingyaogong
|
d52691f2e3
|
[update] default model
|
2026-03-31 13:40:16 +08:00 |
jingyaogong
|
5e9d15614e
|
[update] random seed
|
2026-03-27 21:20:02 +08:00 |
jingyaogong
|
8f3169dba2
|
[update] fp16 inference
|
2026-03-27 16:29:46 +08:00 |
jingyaogong
|
deed5674c4
|
[update] image
|
2026-03-26 15:35:42 +08:00 |
jingyaogong
|
2c24568176
|
[update] change default seq_len
|
2026-03-26 10:09:06 +08:00 |
jingyaogong
|
b24fcdc1f9
|
[update] minimind-3
|
2026-03-25 23:57:45 +08:00 |
jingyaogong
|
855a169582
|
Merge pull request #698 from readlnh/master
[fix] 修复训练脚本中 1-indexed step 与 0-indexed 逻辑混用的问题
|
2026-03-24 13:41:20 +08:00 |
readlnh
|
c88c497795
|
[fix] align log/save last-step check and ETA with 1-indexed step
|
2026-03-24 02:01:40 +01:00 |
readlnh
|
9fe4343b7b
|
[fix] gradient accumulation step alignment
|
2026-03-24 01:45:04 +01:00 |
jingyaogong
|
f798445826
|
[update] empty_think_ratio
|
2026-02-06 19:15:21 +08:00 |
jingyaogong
|
533814ea2d
|
[update] empty_think_ratio
|
2026-02-06 01:36:02 +08:00 |
jingyaogong
|
ec6a14c65d
|
[feat] data process
|
2026-02-06 01:17:57 +08:00 |
jingyaogong
|
69180447af
|
[update] save interval
|
2026-01-30 20:30:50 +08:00 |
jingyaogong
|
9c1f4325f8
|
[update] safe half
|
2026-01-30 20:29:31 +08:00 |
jingyaogong
|
3d2f03cfff
|
[fix] data skip
|
2026-01-18 16:56:29 +08:00 |
jingyaogong
|
f0aa3ba52e
|
[update] shuffle data
|
2026-01-18 16:39:34 +08:00 |
jingyaogong
|
17be26f5b9
|
[fix] max length
|
2026-01-17 13:26:14 +08:00 |
jingyaogong
|
33b0dfbec5
|
[update] pretrain load
|
2026-01-17 12:00:17 +08:00 |