Add model card with paper link and metadata
#1
by nielsr HF Staff - opened
This PR adds a model card for this repository, linking it to the paper Rethinking Reward Models for Multi-Domain Test-Time Scaling and the official GitHub repository. It also populates the YAML metadata with library_name: peft, base_model: Qwen/Qwen3-8B, and pipeline_tag: text-classification.