RLHFlow

/

Llama-3.2-3B-Instruct-Reinforce-Ada-balance-hard

like 0

Follow

RLHFlow 142

This PR enhances the model card by:

• Adding pipeline_tag: text-generation for better discoverability of this LLM for reasoning tasks.
• Including library_name: transformers to enable the automated "How to use" widget, as the model uses a LlamaForCausalLM architecture and is compatible with the Transformers library.
• Linking to the official paper: Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training.
• Adding a direct link to the project's GitHub repository for access to the code and further details.
• Expanding the model description with an overview of the Reinforce-Ada framework, derived from the paper's abstract and the GitHub README.

These updates aim to make the model card more informative and user-friendly for the community.