Verified record · from the answer index

Nemotron-Content-Safety-Reasoning-4B (Experimental)

Nemotron Content Safety Reasoning 4B is a Large Language Model (LLM) classifier designed to function as a dynamic and adaptable guardrail for content safety and dialogue moderation (topic-following). NVIDIA NIM: runs as an API on your own G

model:ngc:nim/nvidia/nemotron-content-safety-reasoning-4b-experimental