Claude
Code & Development
Trust: 55/100 (Fair)llamaguard Guide
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
8,991 starsby zechenzhangagi
When to use llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
How to use llamaguard
llamaguard is a Claude skill in the SKILL.md format. Add it to your Claude environment from the source repository below, then it activates as a user-invocable skill when your task matches its description.
Details
PlatformClaude
CategoryCode & Development
Invocationuser-invocable
Modelany
Maintainerzechenzhangagi
LicenseMIT