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.
Loading preview...
Model tree for
cais/HarmBench-Llama-2-13b-cls-multimodal-behaviorsMost commonly used values from Featherless users
temperature
This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.
top_p
This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.
top_k
This limits the number of top tokens to consider. Set to -1 to consider all tokens.
frequency_penalty
This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.
presence_penalty
This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.
repetition_penalty
This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.
min_p
This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.