Keven16

/

Qwen3-4B-Non-Thinking-RL-Math-Step500

Like 1

This PR adds a model card for the model presented in Rethinking Relative Policy Differences Transfer of On-Policy Distillation. It links the paper and the GitHub repository, and adds relevant metadata (pipeline_tag: text-generation, library_name: transformers) so the model is discoverable and usable with Transformers.