dongboklee

/

gPRM-14B-merged

like 2

This PR adds a comprehensive model card for the gORM-14B-merged model, which is part of the research presented in Rethinking Reward Models for Multi-Domain Test-Time Scaling.

The update includes:

• Relevant metadata: pipeline_tag: text-generation, library_name: transformers, and license: apache-2.0.
• The paper title, a link to its Hugging Face page, and the abstract.
• The GitHub repository link.
• A sample usage code snippet directly from the GitHub README to demonstrate installation and inference.
• The BibTeX citation.

These additions significantly improve the model's discoverability and usability. Please review and merge if everything looks good!