Classifiers for red teaming evaluation in HarmBench
-
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper • 2402.04249 • Published • 3 -
cais/HarmBench-Llama-2-13b-cls
Text Generation • Updated • 13.8k • 14 -
cais/HarmBench-Llama-2-13b-cls-multimodal-behaviors
Text Generation • Updated • 45 -
cais/HarmBench-Mistral-7b-val-cls
Text Generation • Updated • 1.04k • 2