home/categories/machine-learning/orchestra-research-ai-research-skills-07-safety-alignment-llamaguard-skill-md
machine-learningdata-ai
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.
maintainer
Orchestra-Research
更新於 11/20/2025
星標
6563
分支
515
quick start
Installation and usage
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.
安裝
$ install --globalskills.sh
使用
安裝後，您可以通過在終端運行以下命令來使用此技能：
skills use llamaguard