Checkpoints of OPSA on different base models
-
Tuwhy/Qwen3-4B-OPSA
Text Generation • 4B • Updated • 356 • 1 -
Tuwhy/Qwen3.5-9B-OPSA
Image-Text-to-Text • 10B • Updated • 12 -
Tuwhy/Qwen3-1.7B-OPSA
Text Generation • 2B • Updated • 357 -
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement
Paper • 2608.31046 • Published • 110
