Llama 2
Meta
partial detail 11 method fields published
Evaluation
Truthfulness, toxicity and bias of fine-tuned Llama 2-Chat
TruthfulQA (truthful and informative %), ToxiGen (toxic generation %), and BOLD (sentiment by demographic group) on fine-tuned Llama 2-Chat vs pretrained Llama 2 and compared models
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.