|
d701003f8a
|
pretrain过程中会打印10个token以方便观察
|
2025-07-17 00:05:34 +08:00 |
|
|
2797b76939
|
experiment_1.3.0-1.3.2
|
2025-07-13 21:28:46 +08:00 |
|
|
75265f6652
|
使用分类来获取谓词
|
2025-07-05 22:18:32 +08:00 |
|
|
fcab661af9
|
更新了配置文件
|
2025-06-30 19:51:07 +08:00 |
|
|
31eff0e3de
|
更新了两个模型
|
2025-06-30 18:54:42 +08:00 |
|
|
74e9293c9a
|
DynamicKV-LLM Extra v1.0.0
|
2025-06-29 16:01:36 +08:00 |
|
|
d6617702a5
|
DynamicKV-LLM Pretrain v1.2.2:新数据集;使用uv;消除内存泄漏
|
2025-06-25 20:27:28 +08:00 |
|
|
770c34f0e3
|
DynamicKV-LLM Pretrain v1.2.1
|
2025-06-08 02:20:36 +00:00 |
|
|
000e17a93f
|
修正了key分解、负载均衡等错误
|
2025-06-06 11:25:59 +08:00 |
|
|
67c632d010
|
update
|
2025-05-27 11:46:18 +08:00 |
|
Jax922
|
45da3b383b
|
DynamicKV-LLM Pretrain v1.1.2
|
2025-05-23 01:18:08 +08:00 |
|
Jax922
|
42e3d38a3f
|
使用变量代替固定值
|
2025-05-21 08:14:36 +00:00 |
|
Gary
|
d7fe504e1e
|
update
|
2025-05-16 08:38:59 +00:00 |
|
|
089afd6728
|
DynamicKV-LLM Pretrain v1.1.0
|
2025-05-14 00:01:40 +08:00 |
|