tanhuajie2001

/

Reason-RFT-Structure-Perception-Qwen2-VL-2B

like 0

This PR enhances the model card for Reason-RFT by:

• Adding the pipeline_tag: image-text-to-text to improve discoverability on the Hugging Face Hub, as this model performs visual reasoning.
• Including library_name: transformers, as evidenced by the model's configuration files (e.g., config.json referencing Qwen2VLForConditionalGeneration), ensuring compatibility with the automated "How to use" widget.
• Updating the introductory text to clearly state the model's purpose and link to its original paper.
• Refining the "Usage" section to more explicitly guide users to the GitHub repository for detailed instructions and examples.