Michelle0474 182f7853d7 Merge branch 'feat/moe-layer' of github-michelle:RYDE-WORK/lnp_ml into feat/moe-layer ...

# Conflicts:
#	lnp_ml/modeling/layers/llm_prompt.py

2026-06-22 19:46:05 +08:00

..

encoders

Initial commit

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

layers

feat: integrate MolT5 LLM encoder and fix desc dim

2026-06-22 19:39:24 +08:00

__init__.py

Initial commit

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

benchmark.py

Fallback

2026-02-28 18:29:07 +08:00

final_train_optuna_cv.py

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

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

heads.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

models.py

feat: integrate MolT5 LLM encoder and fix desc dim

2026-06-22 19:39:24 +08:00

nested_cv_optuna.py

feat: integrate MolT5 LLM encoder and fix desc dim

2026-06-22 19:39:24 +08:00

predict.py

feat: integrate MolT5 LLM encoder and fix desc dim

2026-06-22 19:39:24 +08:00

pretrain.py

feat(moe): MoE + MolT5 LLM 融合层、消融流水线

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

trainer_balanced.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

trainer.py

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

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

visualization.py

Add loss visualization

2026-01-23 13:40:22 +08:00