24 Commits

Author	SHA1	Message	Date
Michelle0574	aeddf8e1ee	feat: 支持固定超参训练并部署 4 专家稀疏 MoE 模型	2026-08-15 12:22:21 +00:00
Michelle0574	4d4a2c2b7b	Merge branch 'feat/moe-layer' of github.com:RYDE-WORK/lnp_ml into feat/moe-layer	2026-08-14 11:24:21 +00:00
Michelle0574	71f915e683	fix: 修正 size 预测的反归一化并将 MoE+LLM 模型接入应用	2026-08-14 11:24:02 +00:00
Michelle0574	866941039f	feat: final_train_optuna_cv 支持 MoE + Qwen2.5-7B QLoRA + soft-RAG，产出可部署 checkpoint	2026-08-13 10:05:00 +00:00
DicongLi	ec63ac4a69	Fix task-specific Random Forest configuration and results	2026-08-07 17:07:55 +08:00
Michelle0574	bab8203c98	Add MoleculeSTM/MolE/RF/KNN baselines: encoders, scripts, and CV results	2026-07-28 14:14:10 +00:00
Michelle0574	39a2a98fd9	Add full ablation results and CheMeleon/UniMol encoders	2026-07-24 17:56:49 +00:00
Michelle0574	cd9166d63c	feat(moe): MoE + MolT5 LLM 融合层、消融流水线	2026-06-18 08:51:30 +00:00
RYDE-WORK	28b181e194	数据预处理时自动存档总荧光强度的均值与方差,以便于预测时反演荧光强度	2026-03-03 15:48:59 +08:00
RYDE-WORK	447f2543f7	增加baseline评估makefile命令	2026-03-02 11:12:54 +08:00
RYDE-WORK	9e4800b77e	内外部数据LNP四组分比例统一为百分比数,可电离脂质与mRNA比例的搜索范围与四组分解耦	2026-02-28 11:52:55 +08:00
RYDE-WORK	c6e0a974cc	移除其他无用脚本	2026-02-26 19:31:48 +08:00
RYDE-WORK	00f51f37f0	整合与baseline比对的相关脚本	2026-02-26 18:31:22 +08:00
RYDE-WORK	b74f3ab4b2	按照数据预处理脚本变更修正其他相应脚本	2026-02-26 18:07:39 +08:00
RYDE-WORK	0e917ef0d4	引入最新数据&预先修复数据错误&将luminescence为0的分布数据统一为0	2026-02-26 18:00:25 +08:00
RYDE-WORK	39a14e4274	Add final models	2026-01-25 19:19:29 +08:00
RYDE-WORK	871afc5988	Add random CV split	2026-01-23 10:12:25 +08:00
RYDE-WORK	039be54c5a	...	2026-01-22 01:01:29 +08:00
RYDE-WORK	e6a5e5495a	...	2026-01-22 00:24:13 +08:00
RYDE-WORK	e123fc8f3e	update pretrain ratio	2026-01-21 23:36:53 +08:00
RYDE-WORK	a2bfb26dfc	Add CV	2026-01-21 19:35:55 +08:00
RYDE-WORK	6773929ea2	增加LiON的评估指标	2026-01-21 16:20:10 +08:00
RYDE-WORK	0290649df1	...	2026-01-19 10:40:27 +08:00
RYDE-WORK	4c2fdc395f	Initial commit	2026-01-18 21:50:21 +08:00