tanhuajie2001

/

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

like 0

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

• Adding pipeline_tag: image-text-to-text to improve discoverability on the Hub.
• Adding library_name: transformers based on config.json and tokenizer_config.json showing compatibility. This will enable an automated "how to use" widget.
• Updating the main H1 title to reflect the paper and model name: "Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models".
• Removing the descriptive sentence below the previous title, as the new H1 title makes it redundant.

These updates aim to provide clearer and more structured information for users.