Llama 2
Meta
rich detail 14 method fields published
Evaluation
Progression of Models (SFT/RLHF versions on safety and helpfulness)
Progress of SFT then RLHF versions of Llama 2-Chat along Safety and Helpfulness axes measured by in-house safety/helpfulness reward models; GPT-4-based win-rate as a bias check
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.