github
/
minimind-v
mirror of https://github.com/jingyaogong/minimind-v.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
minimind-v/scripts
History
MiniMind-V User 823ce1e4fc [feat] Implement DPO training for driving safety alignment 
- dataset/driving_preferences.jsonl: 56 (prompt, chosen, rejected) pairs
  across 8 safety categories: pedestrian, speed, lane change, weather,
  following distance, traffic signals, emergency vehicles, night driving
- scripts/generate_driving_preferences.py: generator script for the dataset
- trainer/train_dpo_driving.py: custom DPO trainer
  * implements DPO loss from scratch (no trl dependency)
  * frozen reference model + LoRA policy (1.07% trainable params)
  * logs preference accuracy per step
  * saves LoRA adapters or full weights
  * 1 epoch on 56 pairs: loss 0.11, pref_acc 96.4%

Usage:
  uv run python trainer/train_dpo_driving.py     --data_path dataset/driving_preferences.jsonl     --use_lora --epochs 3
 		2026-03-06 05:00:42 +00:00
..
build_knowledge_base.py [feat] Implement LoRA + RAG for DriveMind-V 2026-03-05 01:13:59 +00:00
convert_vlm.py 250427 2025-04-27 18:13:22 +08:00
demo_rag.py [feat] Implement LoRA + RAG for DriveMind-V 2026-03-05 01:13:59 +00:00
generate_driving_preferences.py [feat] Implement DPO training for driving safety alignment 2026-03-06 05:00:42 +00:00
web_demo_vlm.py [feat] update args 2025-10-30 10:50:54 +08:00