Add model card for gPRM-qwen

#1
by nielsr HF Staff - opened

This PR adds a model card for gPRM-qwen (a PEFT adapter based on Qwen/Qwen3-8B). It links the model to the paper Rethinking Reward Models for Multi-Domain Test-Time Scaling and the official GitHub repository, while setting the appropriate metadata tags (such as peft library name, base model, and text-generation pipeline tag).

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment