yangjinluan

/

3H_Merging_Llama3_Harmlessness

like 0

Hi! I'm Niels from the Hugging Face community science team. I noticed this model repository is associated with the paper "Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging".

This PR updates the model card to include:

• library_name: transformers and pipeline_tag: text-generation metadata for better discoverability.
• Relevant tags such as model-merging and RESM.
• A description of the model and its purpose (achieving balanced Helpfulness, Honesty, and Harmlessness alignment via the RESM method).
• A proper BibTeX citation for the associated paper.

Please review and merge if this looks good!