SII-Enigma

/

Llama3.2-8B-Ins-AMPO

like 0

This PR significantly improves the model card for the AMPO model by:

• Adding the apache-2.0 license.
• Specifying library_name: transformers to enable the automated "How to use" widget.
• Adding pipeline_tag: text-generation so users can easily discover the model via filtering.
• Linking the model to the paper More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration.
• Including the paper's abstract for a quick overview.
• Incorporating the introduction, key highlights, and evaluation results (with images) from the GitHub README.
• Providing a direct link to the official GitHub repository for further code and details.
• Adding a "Sample Usage" section with a code snippet from the original GitHub README, adapted to refer to this specific Llama-based model for inference.
• Including the "Models" table and "Acknowledgement" section from the GitHub README for comprehensive information.

Please review and merge this PR.