ShieldGemma-9b is a 9 billion parameter, text-to-text, decoder-only large language model developed by Google, built upon the Gemma 2 architecture. It is specifically designed for safety content moderation, targeting four harm categories: sexually explicit content, dangerous content, hate speech, and harassment. This model excels at classifying user inputs and model outputs against defined safety policies, providing a 'Yes' or 'No' classification based on a structured prompt pattern. It is intended for integration into AI applications requiring robust content filtering capabilities.
Loading preview...
Model tree for
google/shieldgemma-9bMost 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.