AI is happening. The future is updating.Nemotron-Content-Safety-Reasoning-4B
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). Its primary advantage is the ability to enforce custom safety policies. Users can "bring their own safety policy", and the model will adapt its classification and reasoning to meet those specific, user-defined criteria. Use of this model is governed by the NVIDIA Open Model License, Gemma Terms of Use and Gemma Prohibited Use Policy.
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). Its primary advantage is the ability to enforce custom safety policies. Users can "bring their own safety policy", and the model will adapt its classification and reasoning to meet those specific, user-defined criteria. Use of this model is governed by the NVIDIA Open Model License, Gemma Terms of Use and Gemma Prohibited Use Policy.