LMMs-Lab-Turtle

/

Qwen-2.5VL-3B-Cold-Start

like 0

Follow

Turtle-Lab 5

This PR significantly improves the model card for Qwen2.5-VL-3B-Instruct by:

• Adding essential metadata:
  • Adding pipeline_tag: image-text-to-text, ensuring the model is discoverable under the correct category on the Hub (https://huggingface.co/models?pipeline_tag=image-text-to-text).
  • Adding vision-language-model to the existing tags.
• Enriching content:
  • Updating the main title to include the paper name for clarity.
  • Adding the paper title and a direct link to its Hugging Face page: Self-Rewarding Vision-Language Model via Reasoning Decomposition.
  • Including the full paper abstract for a detailed overview.
  • Adding a clear link to the GitHub repository (https://github.com/zli12321/Vision-SR1).
  • Populating the "Model description", "Intended uses & limitations", and "Training and evaluation data" sections with information extracted from the paper and the GitHub README.
  • Adding a "Sample Usage" section with direct code snippets (bash commands) for setup, training, merging, and evaluation response generation, as found in the original GitHub README.
  • Adding the training reward progression image.
  • Adding the citation for the EasyR1 source code as specified in the GitHub README.

These changes make the model card more informative, discoverable, and user-friendly.