yangjinluan

/

3H_Merging_Mistral_Helpfulness_Harmlessness

like 0

This PR improves the model card by:

• Adding the text-generation pipeline tag for better discoverability.
• Specifying the transformers library name to enable the code snippet widget.
• Linking the model to the research paper: Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging.
• Providing a brief summary of the RESM merging method introduced in the paper.