OpenRLHF

/

Llama-3-8b-rm-700k

like 3

Follow

OpenRLHF 51

This PR improves the model card by:

• Adding the pipeline_tag: text-ranking to help users discover this reward model.
• Adding library_name: transformers to indicate compatibility and enable the "Use in Transformers" widget.
• Linking the model to its official paper: REINFORCE++: An Efficient RLHF Algorithm with Robustness to Both Prompt and Reward Models.
• Adding a link to the OpenRLHF GitHub repository.
• Providing a basic Python usage example to demonstrate how to load and use the reward model for scoring text.