Nemotron-3.5-Content-Safety is an NVIDIA model that rates both user input and assistant responses for safety. It supports custom taxonomies and can output structured safety categories. It is intended for integration into LLM applications to enforce responsible AI policies.
Nemotron 3.5 Content Safety is a Foundation models & chat project. Automatically detecting unsafe content in user prompts and model responses according to safety policies. Nemotron 3.5 Content Safety is an open-source project aimed at developers. The project is open source (Open Source). It ships for the web, the command line, and API.
It is developed by NVIDIA (United States), and it first shipped in 2023. Development happens publicly on GitHub with 218 stars. Key capabilities include content safety classification, taxonomy-based labeling, and thinking mode.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do