tencent

/

Hunyuan-MT-7B

like 625

Follow

Tencent 6.15k

This PR significantly improves the model card for Hunyuan-MT by:

• Metadata Enhancements:
  • Adding pipeline_tag: translation to enable better discoverability on the Hugging Face Hub (https://huggingface.co/models?pipeline_tag=translation) and removing the redundant tags: - translation.
  • Explicitly adding license: apache-2.0 for clarity.
• Content Expansion:
  • Adding a clear top-level title, link to the Hunyuan-MT Technical Report, and the paper's abstract for quick understanding.
  • Incorporating comprehensive sections from the project's GitHub README, including "Performance", "Training Data Format", "Train with LLaMA-Factory", "Quantization Compression", "Deployment", and "Contact Us", providing a more complete overview of the model.
  • Updating the demo link to the more specific one found in the GitHub README.
  • Ensuring that existing usage examples with transformers and supported languages tables remain consistent and correctly formatted.

These updates aim to provide users with a richer and more informative model card.