ThinkPRM Process Reward Models that Think -- https://arxiv.org/abs/2504.16828 launch/ThinkPRM-1.5B Text Generation • 2B • Updated 29 days ago • 1.38k • 3 launch/ThinkPRM-7B Text Generation • 8B • Updated May 17 • 146 launch/ThinkPRM-14B Text Generation • 15B • Updated 24 days ago • 9 • 3 launch/thinkprm-1K-verification-cots Viewer • Updated 24 days ago • 1k • 137 • 5
ThinkPRM Process Reward Models that Think -- https://arxiv.org/abs/2504.16828 launch/ThinkPRM-1.5B Text Generation • 2B • Updated 29 days ago • 1.38k • 3 launch/ThinkPRM-7B Text Generation • 8B • Updated May 17 • 146 launch/ThinkPRM-14B Text Generation • 15B • Updated 24 days ago • 9 • 3 launch/thinkprm-1K-verification-cots Viewer • Updated 24 days ago • 1k • 137 • 5