Robot2050

/

MoM

like 0

This PR significantly enhances the model card for the MoM model by providing comprehensive information and improving discoverability.

Key updates include:

• Adding pipeline_tag: text-generation to ensure the model is correctly categorized on the Hugging Face Hub, making it easier for users to find models relevant to text generation tasks.
• Specifying library_name: transformers in the metadata, indicating the model's compatibility with the Hugging Face transformers library, as evidenced by its Qwen2ForCausalLM architecture and transformers_version in config.json.
• Incorporating the full paper abstract, offering users a quick overview of the model's purpose and methodology.
• Integrating detailed sections from the official GitHub README, such as "Who Should Pay Attention to Our Work?", "Core Contributions", "Quick Start" (for running project-specific scripts), and "Results", to provide a complete understanding of the project.
• Updating the badges to include links to the arXiv paper, Hugging Face paper, Hugging Face dataset, and specific model checkpoints (MemReader 1.5B, 3B, 7B) for quick access to all relevant resources.
• Removing the redundant "File information" section.

These changes collectively make the model card much more informative and user-friendly.