rzzhan

/

ThinMQM-8B

like 0

This PR aims to significantly improve the model card by making the following updates:

• Corrected License: The license in the metadata has been updated from mit to apache-2.0 to accurately reflect the license stated in both the current model card content and the associated GitHub repository.
• Added Pipeline Tag: The pipeline_tag: text-generation has been added. This categorizes the model as a language model performing text generation tasks (generating reasoning/evaluations for MT) and improves its discoverability on the Hugging Face Hub.
• Added Library Name: The library_name: transformers has been included. Evidence from config.json (transformers_version) and the GitHub README's acknowledgments (mentioning transformers for model/data loading) confirms compatibility. This will enable an automated "how to use" code snippet on the model page, enhancing user experience.
• Enriched Content: The model card content has been expanded to include the paper abstract and key sections from the GitHub README, such as "Introduction", "Quick Start", "Configuration" (with detailed model templates and decoding recommendations), and "Meta-Evaluation". This provides a more comprehensive overview of the model, its usage, and its performance.

Existing relevant information, such as the paper link, GitHub repository link, and original badges, has been preserved.