tanhuajie2001

/

Reason-RFT-Zero-Visual-Counting-Qwen2-VL-2B

like 0

This PR updates the model card for "Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models."

Key changes include:

• Metadata: Added pipeline_tag: image-text-to-text and library_name: transformers to improve model discoverability and enable the automated "how to use" widget. The transformers library compatibility is evidenced by the config.json and tokenizer_config.json files.
• Paper Link: Added a direct link to the Hugging Face paper page (https://huggingface.co/papers/2503.20752) after the model title for better prominence.
• News Section: Updated with more recent and complete entries from the GitHub repository's README.
• Sample Usage: Replaced the generic usage instruction with a detailed "Sample Usage" section, featuring code snippets for environment setup and training, extracted directly from the project's GitHub README.
• Citations: The citation section has been updated to focus on the primary Reason-RFT paper.

These changes aim to make the model card more informative and user-friendly for the Hugging Face community.