# Multilingual content moderation

DuoGuard-0.5B is a multilingual, decoder-only large language model-based classifier, specifically designed for safety content moderation across 12 different subcategories.

An 8-billion-parameter brand safety classification model optimized based on Llama 3.1, specifically designed for Apple chip devices

Llama Guard 3 is a content safety classifier fine-tuned from the Llama-3.1-8B pre-trained model for content moderation of LLM inputs and responses.

A content security classification model fine-tuned based on Llama-3.1-8B, supporting content moderation of input/response in 8 languages