Llama Guard
Llama Guard is an LLM-based input-output safeguard model geared towards Human-AI conversation use cases.
Features
- AI-Powered
Tags
- llama-3
- ai-model
- safeguarding
- ai-safety
- huggingface
- llama
- safety
- ai-guardrails
- safety-management
Llama Guard News & Activities
Recent activities
- POX updated Llama Guard
- POX added Llama Guard as alternative to Toxic Prompt RoBERTa
POX added Llama Guard as alternative to ShieldGemma and WildGuard- POX added Llama Guard
Llama Guard information
Developed by
Meta Licensing
Open Source and Free product.Alternatives
3 alternatives listedSupported Languages
- English
AlternativeTo Category
AI Tools & Services
What is Llama Guard?
Llama Guard is an LLM-based input-output safeguard model geared towards Human-AI conversation use cases.
The model incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks found in LLM prompts (i.e., prompt classification). This taxonomy is also instrumental in classifying the responses generated by LLMs to these prompts, a process referred to as response classification.
Llama Guard comes in three flavors now: Llama Guard 3 1B, Llama Guard 3 8B and Llama Guard 3 11B-Vision. The first two models are text only, and the third supports the same vision understanding capabilities as the base Llama 3.2 11B-Vision model.
All the models are multilingual–for text-only prompts–and follow the categories defined by the ML Commons consortium.