notus
notus copied to clipboard
Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach
Results
2
notus issues
Sort by
recently updated
recently updated
newest added
Based on our curation efforts, we spotted a bug in the `overall_score` of UltraFeedback AI Critique score. TLDR: Responses getting the lowest score (1 or less) become a high score...
team: ml