xxxllz

/

ChartCoder

like 4

This PR significantly enhances the model card for ChartCoder by:

• Adding key metadata: pipeline_tag: image-text-to-text, library_name: transformers, license: cc-by-nc-4.0, and tags: - code-generation. This improves discoverability on the Hub (e.g., at https://huggingface.co/models?pipeline_tag=image-text-to-text) and indicates compatibility with the Hugging Face Transformers library.
• Enriching the introductory section with an "About ChartCoder" summary derived from the paper's abstract.
• Integrating comprehensive details from the project's GitHub repository, including "Notes", "News", "Overview", "Models", and "Data" sections, along with updated image links to ensure proper rendering.
• Providing a clear "Installation" and "Training" guide for local setup.
• Adding a practical "Inference (Sample Usage)" code snippet using the transformers library, enabling users to easily load and run the model.
• Updating the top links with badges for datasets, the model itself, the arXiv paper, and the GitHub repository.

These changes provide a much richer and more actionable resource for users exploring ChartCoder on the Hugging Face Hub.