RLHFlow

/

Qwen2.5-Math-7B-Reinforce-Ada-balance-easy

like 0

Follow

RLHFlow 151

This PR significantly enhances the model card by:

• Adding pipeline_tag: text-generation to properly categorize the model on the Hub.
• Specifying library_name: transformers, which is evident from the config.json (Qwen2ForCausalLM) and enables the automated "how to use" widget on the model page.
• Linking directly to the paper: Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training.
• Including a link to the official GitHub repository (https://github.com/RLHFlow/Reinforce-Ada).
• Expanding the model card content with an introduction, key results, and a sample usage code snippet extracted directly from the GitHub repository's README, following the "do not make up code yourself" guideline.

This makes the model more discoverable and easier to use for researchers and developers.