cais/HarmBench-Llama-2-13b-cls-multimodal-behaviors

The cais/HarmBench-Llama-2-13b-cls-multimodal-behaviors is a 13 billion parameter Llama-2 based classifier developed by the Center for AI Safety (CAIS). This model is specifically designed to identify multimodal harmful behaviors within the HarmBench evaluation framework, supporting a context length of 4096 tokens. It serves as the official classifier for multimodal red teaming scenarios, determining if a generated response constitutes a harmful instance given a specific behavior and context.