Rethinking OPD - a Thinking-Space Collection

Thinking-Space 's Collections

Rethinking OPD

updated about 18 hours ago

This collection includes the models used in paper "Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe"

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published Apr 14 • 116
Thinking-Space/Qwen3-1.7B-SFT

Text Generation • 2B • Updated May 12 • 2.31k • 4
Thinking-Space/Qwen3-4B-Base-GRPO

Text Generation • 4B • Updated May 3 • 580 • 3
Thinking-Space/OpenThought3-Qwen3-4B

Viewer • Updated May 12 • 305k • 73 • 2
Thinking-Space/Qwen3-1.7B-Base-OPD

Text Generation • 2B • Updated Jun 3 • 116