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.

$ インストール

git clone https://github.com/zechenzhangAGI/AI-research-SKILLs /tmp/AI-research-SKILLs && cp -r /tmp/AI-research-SKILLs/07-safety-alignment/llamaguard ~/.claude/skills/AI-research-SKILLs

// tip: Run this command in your terminal to install the skill