Add comprehensive model card for Visual Programmability: Code-as-Thought
#1
by
nielsr
HF Staff
- opened
This PR significantly enhances the model card for the model associated with the paper "Visual Programmability: A Guide for Code-as-Thought in Chart Understanding".
Key improvements include:
- Adding
pipeline_tag: image-text-to-textto enable discoverability on the Hugging Face Hub (e.g., at https://huggingface.co/models?pipeline_tag=image-text-to-text). - Specifying
library_name: transformersbased onconfig.jsonand acknowledgements, which will automatically enable a "How to use" widget on the model page with a runnable code snippet. - Linking the model to its paper: Visual Programmability: A Guide for Code-as-Thought in Chart Understanding.
- Including links to the project page and the GitHub repository for easy access to more information and code.
- Adding the full paper abstract, associated models and datasets, citation, and acknowledgements.
- No direct sample usage code snippet is included, as no suitable inference example was found in the provided GitHub README content for this specific model, adhering to the guidelines. A "Usage" section directs users to the GitHub repository for detailed instructions.
These updates aim to provide users with a richer understanding of the model's capabilities and facilitate its integration into their workflows.