LMMs-Lab-Turtle

/

SelfRewarded-R1-7B

like 4

Follow

Turtle-Lab 6

This PR significantly improves the model card for Vision-SR1 by:

• Adding pipeline_tag: image-text-to-text to the metadata, which enhances discoverability at https://huggingface.co/models?pipeline_tag=image-text-to-text.
• Including library_name: transformers in the metadata, based on explicit evidence in config.json and the GitHub README, enabling the automated "Use in Transformers" widget.
• Incorporating the full paper abstract to provide a comprehensive overview of the model's methodology and capabilities.
• Linking to the official Hugging Face paper page: Self-Rewarding Vision-Language Model via Reasoning Decomposition.
• Providing a direct link to the official GitHub repository for code and further details: https://github.com/zli12321/Vision-SR1.
• Populating the main content with a detailed description adapted from the GitHub README, including information about the model, datasets, and related Hugging Face artifacts.
• Including the recommended citation for the codebase.

Please review and merge this PR if these changes align with your expectations.