Llama 2
Meta
rich detail 14 method fields published
Evaluation
Safety benchmarks for pretrained models (TruthfulQA, ToxiGen, BOLD)
Three automatic safety benchmarks: TruthfulQA (truthfulness, % truthful and informative), ToxiGen (toxicity, % toxic generations), BOLD (bias, sentiment variation with demographic attributes); decoding with temperature 0.1 and top-p 0.9
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.