ViperEkura 1d54491809 refactor: 改用递归子模块 init 替代统一 normal_(0.006) ...

- Embedding.reset_parameters: normal_(std=0.02)
- Linear.reset_parameters: kaiming_uniform_ + uniform_ bias
- Transformer._init_weights 通过 apply 递归调用子模块 reset_parameters
- 移除全局 normal_(0.006) 覆盖，各模块使用更合适的分布

2026-05-17 10:44:18 +08:00

..

components

refactor: 改用递归子模块 init 替代统一 normal_(0.006)

2026-05-17 10:44:18 +08:00

__init__.py

refactor: 拆分 module.py 为 components 子包

2026-05-15 20:08:36 +08:00

automodel.py

refactor: Config序列化统一BaseConfig基类

2026-05-16 22:06:39 +08:00

transformer.py

refactor: 改用递归子模块 init 替代统一 normal_(0.006)

2026-05-17 10:44:18 +08:00