ViperEkura 88ec63121d feat : GPT-2 residual scaling weight init ...

- Linear: normal(0, init_std) replaces kaiming_uniform_(a=sqrt(5))
- o_proj / mlp.down: init_std = 0.02 / sqrt(2 * n_layers)
- MoE: expert down scaled by 1/sqrt(1/n_shared + 1/K)
- Embedding: normal(0, 0.02), unchanged

2026-06-25 15:08:31 +08:00

..

components

feat : GPT-2 residual scaling weight init

2026-06-25 15:08:31 +08:00

__init__.py

feat: 新增LoRA微调模块

2026-05-25 20:15:31 +08:00

automodel.py

refactor : 移除 -> None 返回值标注，拆分 FSDP 参数，新增 mmap 数据集存储

2026-05-28 13:57:06 +08:00

encoder.py

refactor : neftune_alpha 在 Embedding 构造时传入，由模型配置链路负责

2026-06-19 14:23:27 +08:00

transformer.py

refactor : neftune_alpha 在 Embedding 构造时传入，由模型配置链路负责

2026-06-19 14:23:27 +08:00