Michelle0574
22e83122e7
feat: Qwen SoftRAG(RAG prompt/soft token/QLoRA)+ Morgan 检索旁路与实验结果
2026-07-07 17:47:34 +00:00
Michelle0474
0fc72a9474
Add Qwen2.5-7B MolRAG encoder branch + dual-seed results
...
- llm_prompt.py: RAG prompt encoding (use_rag), Qwen support, set_retrieval_pool (leak-safe, train-only pool)
- models.py: use_rag/rag_top_k passthrough to LLMPromptEncoder
- nested_cv_optuna.py: --use-rag CLI, per-fold retrieval pool (防泄漏), slim checkpoint (skip frozen LLM weights)
- Qwen+RAG results: seed42 delivery R2=0.2151, seed123=0.1558 (mean 0.185), best LLM encoder so far
2026-06-28 20:42:27 +08:00
Michelle0474
c0aa30f2bb
Add 6-variant ablation results (baseline/moe/llm_molt5/llm_biot5/both_molt5/both_biot5)
...
- Updated ablation_summary.csv with full 6-variant comparison
- Updated run_all.sh to run 6 variants (added BioT5 variants)
- Added per-fold json artifacts (best_params/test_metrics/splits/history/summary)
- Model weights (.pt) excluded per .gitignore
2026-06-24 15:33:07 +08:00
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
175b07473c
Final Model
2026-03-02 14:51:54 +08:00
RYDE-WORK
ca459470df
Add new final model
2026-02-28 16:28:56 +08:00
RYDE-WORK
3a45c0641c
...
2026-02-26 20:06:27 +08:00
RYDE-WORK
a9392aa780
Update models and UI
2026-02-11 16:49:28 +08:00
RYDE-WORK
39a14e4274
Add final models
2026-01-25 19:19:29 +08:00
RYDE-WORK
a56637c8ac
Add loss visualization
2026-01-23 13:40:22 +08:00
RYDE-WORK
ac4246c2b7
Add train_cv(without pretrain)
2026-01-22 18:06:13 +08:00
RYDE-WORK
47bbb64c66
Add more metrics
2026-01-22 17:06:24 +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
c392b48994
Add CV results
2026-01-21 22:57:44 +08:00
RYDE-WORK
e1c85c83ba
CV results
2026-01-21 20:10:48 +08:00
RYDE-WORK
a2bfb26dfc
Add CV
2026-01-21 19:35:55 +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