Qwen3-1.7B Process Reward Model for Math

Training target: Qwen/Qwen3-1.7B

Intended method: TRL PRMTrainer on step-level math supervision from trl-lib/math_shepherd.

Status: repository created. Training script/job launch pending due sandbox duplication rate-limit in the current session.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support