pasztorb/Llama-3.1-Tulu-3-8B-SLHF

Stackelberg Learning from Human Feedback

Preference finetuned model using the Stackelberg Learning from Human Feedback approach for general conversational applications.

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: Barna Pasztor, Thomas Kleine Buening, Andreas Krause
• Model type: A model trained on a mix of publicly available, synthetic and human-created datasets using LLM-as-a-judge (Skywork/Skywork-Critic-Llama-3.1-70B).
• Language(s) (NLP): Primarily English
• License: Llama 3.1 Community License Agreement
• Finetuned from model: meta-llama/Llama-3.1-8B

Model Sources

• Repository: GitHub
• Paper: ArXiv Preprint