Verified record · from the answer index

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. Inte

skill:orchestra-research/ai-research-skills/llamaguard · published by orchestra-research · source repository