Michelle0574 33fe637364 feat(training): size 头正则化(dropout+weight_decay)与 size z-score，更新消融汇总

2026-06-20 02:45:00 +00:00

..

__init__.py

feat(training): size 头正则化(dropout+weight_decay)与 size z-score，更新消融汇总

2026-06-20 02:45:00 +00:00

bidirectional_cross_attention.py

Initial commit

2026-01-18 21:50:21 +08:00

fusion.py

feat(moe): MoE + MolT5 LLM 融合层、消融流水线

2026-06-18 08:51:30 +00:00

llm_prompt.py

feat(moe): MoE + MolT5 LLM 融合层、消融流水线

2026-06-18 08:51:30 +00:00

moe.py

Add Mixture-of-Experts (MoE) layer support across modeling pipeline

2026-05-26 15:26:18 +08:00

set_transformer.py

feat(moe): MoE + MolT5 LLM 融合层、消融流水线

2026-06-18 08:51:30 +00:00

token_projector.py

Initial commit

2026-01-18 21:50:21 +08:00