tanhuajie2001

/

Reason-RFT-Zero-Spatial-Transformation-Qwen2-VL-2B

like 0

This PR enhances the model card by:

• Adding pipeline_tag: image-text-to-text for better discoverability on the Hugging Face Hub (e.g., at https://huggingface.co/models?pipeline_tag=image-text-to-text).
• Including library_name: transformers to enable the automated "how to use" widget, as the model is compatible with the transformers library.
• Correcting the main title of the model card to reflect the paper's title.
• Updating the "News" section with more recent information from the GitHub repository.
• Adding the "Pipeline" and "Embodied Visual Reasoning Tasks" sections from the GitHub README to provide more comprehensive information about the model and its applications.
• Updating the "Citation" section to include all relevant BibTeX entries from the GitHub repository.

This ensures the model card accurately reflects the model's capabilities and improves user experience.