jingyaogong
|
c090b69c4d
|
[update] align loss
|
2026-01-15 00:56:32 +08:00 |
jingyaogong
|
1279a61681
|
[update] prompt prefill
|
2026-01-13 17:46:54 +08:00 |
jingyaogong
|
9d898576ac
|
[update] aux loss
|
2026-01-01 22:41:46 +08:00 |
jingyaogong
|
c65335b56f
|
[fix] experts unused
|
2025-12-31 21:47:04 +08:00 |
jingyaogong
|
5129f0e2a2
|
[fix] dtype & lr
|
2025-12-09 13:01:38 +08:00 |
jingyaogong
|
ecd1ae1563
|
[fix] reduce aux_loss_alpha
|
2025-12-05 23:08:29 +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 |
jingyaogong
|
f5374dc87f
|
[fix] model attn_mask
|
2025-11-19 22:26:53 +08:00 |
jingyaogong
|
a044578d73
|
[fix] update model
|
2025-11-18 13:07:20 +08:00 |
yuyu5333
|
7d02ce673c
|
fix: attn_forwad when is_causal=True assert attn_mask is None
|
2025-11-18 03:17:17 +00:00 |
jingyaogong
|
4e35fb9da8
|
[fix] update model
|
2025-10-17 00:09:32 +08:00 |
jingyaogong
|
29454c31af
|
fix bugs
|
2025-04-27 09:56:49 +08:00 |
jingyaogong
|
a62faf34bd
|
250426
|
2025-04-26 10:05:47 +08:00 |