X-GenGroup

/

PaCo-Reward-7B

like 2

Follow

X-Gen Group 7

This PR adds a comprehensive model card for the PaCo-Reward-7B model, a component of the PaCo-RL framework.

It includes:

• Relevant metadata: pipeline_tag (image-text-to-text) and library_name (transformers), derived from model configuration and functionality.
• Links to the research paper (PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling), the project page (https://x-gengroup.github.io/HomePage_PaCo-RL/), and the GitHub repository (https://github.com/X-GenGroup/PaCo-RL).
• A concise description of the model based on the paper abstract.
• The 'Overview' and 'Model Zoo' sections from the GitHub README to provide better context and discoverability of related models.
• The BibTeX citation for the paper.

The license and a code snippet for sample usage are omitted as no explicit evidence was found in the provided documentation, adhering to the safety guidelines.

Please review and merge if these improvements are satisfactory.