Commit Graph

281 Commits (8ace03f068b3d67183191167bafd22df278d9e0f)

Author SHA1 Message Date
jingyaogong 8ace03f068 [feat] update config 2025-12-31 10:29:13 +08:00
jingyaogong 6ee867fffc [feat] update lr 2025-12-31 10:27:09 +08:00
jingyaogong cc40ff6f45 [feat] compatible tokenizer 2025-12-31 10:26:46 +08:00
jingyaogong bc6f6dea99 [feat] stream load data 2025-12-28 16:58:52 +08:00
jingyaogong fc2eeff509 [feat] remove empty_cache 2025-12-27 07:14:36 +08:00
jingyaogong 658ddcae3a [feat] explicit left padding 2025-12-23 18:59:48 +08:00
jingyaogong 4cbca65883 [fix] lora weight 2025-12-22 21:27:29 +08:00
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