Process Reward Models Model and Datasets for Qwen 2.5 Math PRM 7B axolotl-ai-co/Qwen2.5-Math-PRM-7B Token Classification • Updated Feb 18 • 20 • 1 axolotl-ai-co/prm800k_phase_1 Viewer • Updated Feb 7 • 41.2k • 96 • 2 axolotl-ai-co/prm800k_phase_2 Viewer • Updated Feb 7 • 492k • 66 • 1 axolotl-ai-co/Math-Shepherd Viewer • Updated Feb 3 • 445k • 49 • 1