Jennny

/

eng_rm_1e5_700

like 0

This PR adds a model card for the Engagement Process Reward Model (PRM) introduced in the paper "Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards".

The model card includes:

• Metadata for the transformers library and text-classification pipeline tag.
• Information about the model's role in the MAHALO framework.
• Links to the paper and the official GitHub repository.
• The BibTeX citation for the work.