jingyaogong
|
0664b383e4
|
Merge pull request #594 from whiteswordLI/fix/lora-load-ddp-weights
Fix: support loading DDP-saved LoRA weights for inference
|
2025-12-22 21:19:16 +08:00 |
whitesword
|
65b648be32
|
Fix: support loading DDP-saved LoRA weights for inference
|
2025-12-22 20:50:25 +08:00 |
jingyaogong
|
dacd4e5121
|
[feat] adjust seq length
|
2025-12-14 20:41:58 +08:00 |
jingyaogong
|
b813b562e2
|
[feat] update readme
|
2025-12-11 15:45:50 +08:00 |
jingyaogong
|
37300329c5
|
[fix] dtype & lr
|
2025-12-09 13:01:38 +08:00 |
jingyaogong
|
b6b0c8f675
|
Merge pull request #571 from dyhuachi/dyhuachi-patch-1
[fix] Refactor get_lr function to include min_lr calculation
|
2025-12-09 12:59:11 +08:00 |
dyhuachi
|
8fcc81696d
|
[fix] Refactor get_lr function to include min_lr calculation
这里的退火算法会让参数里的lr的起始值变成原来lr的1.1倍,作出如下修改
|
2025-12-06 17:09:51 +08:00 |
jingyaogong
|
7614a3bf90
|
[fix] reduce aux_loss_alpha
|
2025-12-05 23:08:29 +08:00 |
jingyaogong
|
95bcb7ba19
|
[fix] cuda memory #559
|
2025-12-01 16:17:43 +08:00 |
jingyaogong
|
295b9ad443
|
[feat] update yarn
|
2025-12-01 16:15:05 +08:00 |
jingyaogong
|
cafc3b22df
|
[feat] release memory
|
2025-11-27 19:39:49 +08:00 |
jingyaogong
|
3382c90246
|
[fix] ppo mask
|
2025-11-19 23:39:02 +08:00 |
jingyaogong
|
21cadea5f5
|
[fix] model attn_mask
|
2025-11-19 22:26:53 +08:00 |
jingyaogong
|
7aef898647
|
[fix] update model
|
2025-11-18 13:07:20 +08:00 |
jingyaogong
|
22f82be681
|
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
|
9c29046d2e
|
fix: attn_forwad when is_causal=True assert attn_mask is None
|
2025-11-18 03:17:17 +00:00 |
jingyaogong
|
c8727733f3
|
[fix] prompt length calculate
|
2025-11-15 18:25:37 +08:00 |
jingyaogong
|
d334a6f9f4
|
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
|
7088cc886f
|
[feat] add MNN support to README.
|
2025-11-10 21:59:22 +08:00 |
jingyaogong
|
d7cc69d4de
|
[fix] model-name
|
2025-11-07 19:38:20 +08:00 |
jingyaogong
|
23d341df97
|
[fix] harmonize template
|
2025-11-06 13:14:08 +08:00 |
jingyaogong
|
86d5cc70ec
|
[feat] clear cache
|
2025-11-06 13:12:28 +08:00 |
jingyaogong
|
289ca01679
|
[fix] harmonize template
|
2025-11-02 23:18:11 +08:00 |
jingyaogong
|
7c3d660eec
|
[feat] update import
|
2025-10-31 23:45:55 +08:00 |
jingyaogong
|
fdc6c5db5d
|
[feat] update readme
|
2025-10-30 23:39:25 +08:00 |
jingyaogong
|
f10df43275
|
[feat] update readme
|
2025-10-30 23:30:12 +08:00 |
jingyaogong
|
1869dc8315
|
[feat] update readme
|
2025-10-30 23:27:15 +08:00 |
jingyaogong
|
e544126ab5
|
[feat] update datasets
|
2025-10-30 11:08:13 +08:00 |
jingyaogong
|
e840d8b83e
|
[feat] update args
|
2025-10-30 10:48:31 +08:00 |
jingyaogong
|
ccab16a9b9
|
[feat] add args
|
2025-10-30 10:05:12 +08:00 |
jingyaogong
|
d3f9161cec
|
[feat] update readme
|
2025-10-29 12:13:25 +08:00 |
jingyaogong
|
230b29b94a
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
jingyaogong
|
e29f695998
|
[feat] update trainer
|
2025-10-29 00:52:37 +08:00 |
jingyaogong
|
cd576b58e8
|
[feat] update trainer
|
2025-10-28 23:30:10 +08:00 |
jingyaogong
|
f48568f62e
|
[feat] update readme
|
2025-10-27 16:31:40 +08:00 |
jingyaogong
|
db16c62412
|
[feat] update readme
|
2025-10-26 18:52:50 +08:00 |
jingyaogong
|
d74d8451c7
|
[feat] update eval-llm
|
2025-10-26 18:52:01 +08:00 |
jingyaogong
|
43726a7c34
|
[feat] pause-training
|
2025-10-26 18:49:52 +08:00 |
jingyaogong
|
6c78df4c64
|
[feat] update readme
|
2025-10-24 01:18:33 +08:00 |
jingyaogong
|
bded87a804
|
[feat] update readme
|
2025-10-24 00:45:11 +08:00 |
jingyaogong
|
c3ca123216
|
[feat] update requirements
|
2025-10-23 23:54:55 +08:00 |
jingyaogong
|
dcf04e9136
|
[feat] update requirements
|
2025-10-23 23:50:21 +08:00 |
jingyaogong
|
c99f12746e
|
[feat] update readme
|
2025-10-23 23:23:52 +08:00 |
jingyaogong
|
5e72e0f4d5
|
[feat] update readme
|
2025-10-23 20:23:46 +08:00 |
jingyaogong
|
36b6ada80b
|
[feat] repetition-penalty
|
2025-10-23 20:23:25 +08:00 |
jingyaogong
|
8284d44039
|
[feat] convert2llama
|
2025-10-23 20:22:42 +08:00 |
jingyaogong
|
8d1778a186
|
[feat] shuffle data
|
2025-10-23 20:13:28 +08:00 |
jingyaogong
|
3658bdb20d
|
[fix] loss-issues-430
|
2025-10-23 19:08:42 +08:00 |
jingyaogong
|
00c24568dc
|
[fix] restore
|
2025-10-23 19:00:06 +08:00 |
jingyaogong
|
fa935a496e
|
[fix] issue-431
|
2025-10-23 18:56:30 +08:00 |