Checkpoints of OPSA on different base models
Yi Ding
Tuwhy
AI & ML interests
None yet
Recent Activity
authored a paper about 7 hours ago
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement updated a model about 12 hours ago
Tuwhy/Qwen3-4B-OPSA updated a model about 12 hours ago
Tuwhy/Qwen3.5-9B-OPSAOrganizations
models 20
Tuwhy/Qwen3-4B-OPSA
Text Generation • 4B • Updated • 356
Tuwhy/Qwen3.5-9B-OPSA
Image-Text-to-Text • 10B • Updated • 12
Tuwhy/Qwen3-1.7B-OPSA
Text Generation • 2B • Updated • 357
Tuwhy/Octopus-8B
Image-Text-to-Text • 9B • Updated • 12
Tuwhy/Qwen3-VL-8B-GRPO-n16
9B • Updated • 5
Tuwhy/Qwen3-VL-8B-DAPO-n16
9B • Updated • 6
Tuwhy/Qwen3-VL-8B-SRPO-n16
9B • Updated • 4
Tuwhy/Qwen3-VL-8B-SCPO-random
9B • Updated • 3
Tuwhy/Qwen3-VL-8B-SRPO-n8
9B • Updated • 4
Tuwhy/Qwen3-VL-8B-GSPO-n8
9B • Updated • 4
datasets 7
Tuwhy/mathverse_testmini
Viewer • Updated • 3.94k • 14
Tuwhy/mmmu_val
Viewer • Updated • 900 • 14
Tuwhy/mathvision
Viewer • Updated • 304 • 22
Tuwhy/mathvista_testmini
Viewer • Updated • 1k • 11
Tuwhy/virl_39k
Viewer • Updated • 36.6k • 6
Tuwhy/MIS_Test
Updated • 431
Tuwhy/MIS_Train
Viewer • Updated • 3.93k • 423