Llama Guard 3 (8B) API

Basic Information

• Model Name: Meta Llama Guard 3 (8B)
• Model Type: Language Model for Input/Output Safeguarding

Overview:

Meta Llama Guard 3 (8B) is a language model designed to provide input and output safeguards for human-AI conversations. It focuses on content moderation and safety, ensuring the responses generated by AI systems adhere to predefined safety standards.

Key Features:

• Fine-tuned for content safety classification across multiple languages.
• Capable of classifying prompts and responses to identify safe or unsafe content.
• Implements a safety risk taxonomy for effective moderation.
• Supports zero-shot and few-shot prompting for diverse applications.
• Generates binary decision scores for prompt safety evaluation.

Intended Use:

The model is intended for developers looking to enhance the safety of AI systems, particularly in applications involving conversational agents, customer support bots, and any scenario where user interaction with AI is prevalent.

Language Support:

Meta Llama Guard 3 supports multiple languages, making it suitable for global applications in content moderation.

Architecture:

The model is based on the Llama 3.1 architecture, utilizing an optimized transformer design that incorporates supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) to improve response quality and safety.

Use cases

• Content Moderation: Automated filtering of unsafe input/output in chatbots
• AI Safety Governance: Enforce compliance in LLM-based apps
• Tool/Agent Integration: Pre-checks for chatbot-generated messages before dispatch
• Multilingual Deployments: Supported across 8 languages
• Interactive Safety Layers: Combined with output generation models like Llama 3.1 8B

Capabilities

• Streaming