google/shieldgemma-9b
TEXT GENERATIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:16kPublished:Jul 16, 2024License:gemmaArchitecture:Transformer0.0K Gated Warm

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...