Llama 3.2
Meta
partial detail 8 method fields published
Evaluation
Scaled evaluations with Purple Llama safeguards
Scaled evaluations using dedicated adversarial evaluation datasets, evaluating systems composed of Llama models and Purple Llama safeguards for input prompt and output response filtering
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.