Data and checkpoints of M3OPD-Reasoner, an open recipe for reasoning vision-language models with multi-teacher on-policy distillation.
Nguyen Quang Trung
ngqtrung
AI & ML interests
None yet
Recent Activity
updated a collection 2 days ago
M3OPD-Reasoner updated a model 2 days ago
ngqtrung/M3OPD-Reasoner-9B published a model 2 days ago
ngqtrung/M3OPD-Reasoner-9BOrganizations
M3OPD-Reasoner
Data and checkpoints of M3OPD-Reasoner, an open recipe for reasoning vision-language models with multi-teacher on-policy distillation.
MOPD: multi-teacher on-policy distillation (Qwen3.5-9B)
Domain SFT teachers, GSPO teachers and the training data (SFT v4, RL v2 with full media) of the MOPD project.
models 30
ngqtrung/M3OPD-Reasoner-9B
Image-Text-to-Text • 9B • Updated • 22
ngqtrung/M3OPD-MixRL-Baseline-9B
Image-Text-to-Text • 9B • Updated • 17
ngqtrung/M3OPD-MOPD-9B
Image-Text-to-Text • 9B • Updated • 18
ngqtrung/M3OPD-Teacher-Video-9B
Image-Text-to-Text • 9B • Updated • 21
ngqtrung/M3OPD-Teacher-ImagePerception-9B
Image-Text-to-Text • 9B • Updated • 16
ngqtrung/M3OPD-Teacher-ImageSTEM-9B
Image-Text-to-Text • 9B • Updated • 17
ngqtrung/ee6405-misinfo-detection
Text Classification • Updated
ngqtrung/Qwen3.5-9B-MOPD-SFT-vid
Image-Text-to-Text • 9B • Updated • 38
ngqtrung/Qwen3.5-9B-MOPD-SFT-imgp
Image-Text-to-Text • 9B • Updated • 36
ngqtrung/Qwen3.5-9B-MOPD-SFT-imgr
Image-Text-to-Text • 9B • Updated • 31
datasets 64
ngqtrung/M3OPD-SFT-1.35M
Viewer • Updated • 1.35M • 53
ngqtrung/M3OPD-RL-193K
Viewer • Updated • 193k • 54
ngqtrung/mopd-data
Viewer • Updated • 3.19M • 81
ngqtrung/EE6108-workshop-video
Viewer • Updated • 1 • 22
ngqtrung/ptl-crossing-check
Viewer • Updated • 5.06k • 1.7k
ngqtrung/Video-HopChain
Viewer • Updated • 23.6k • 402
ngqtrung/emilia-dpo
Viewer • Updated • 88k • 1.03k
ngqtrung/cs-dialogue-dpo
Viewer • Updated • 14.2k • 478
ngqtrung/IMAVB
Viewer • Updated • 2k • 545
ngqtrung/aidm-dogs-vs-cats-results
Viewer • Updated • 114 • 275