qiuk6

/

RobusTok

like 1

This PR significantly enhances the model card for "Image Tokenizer Needs Post-Training" (RobusTok).

Key improvements include:

• Adding the pipeline_tag: unconditional-image-generation to improve discoverability on the Hugging Face Hub (e.g., https://huggingface.co/models?pipeline_tag=unconditional-image-generation).
• Linking the model directly to its paper: Image Tokenizer Needs Post-Training.
• Including links to the project page and the GitHub repository for easy access to more information and code.
• Providing a summary of the model's purpose and key features based on the paper's abstract and GitHub README.
• Including the Model Zoo table with direct links to weights.
• Directing users to the GitHub repository for detailed usage examples and installation instructions, as the model's inference requires custom scripts.
• Adding a visualization demonstrating the improvements.
• Including the academic citation for the work.

Please review these updates.