Llama 3.1 NemoGuard 8B ContentSafety NIM#

About the Microservice#

The microservice serves a GPU-accelerated LLM model that performs content moderation for building trustworthy LLM applications. The LLM model detects harmful content in user messages or bot responses.

The model is a content safety model trained by NVIDIA from a Llama 3.1 8B Instruct base model. The model is trained using the Nemotron Content Safety Dataset V2–a carefully curated collection of 30 thousand dialog samples in the content harm taxonomy. The dataset is formerly known as the Aegis AI Content Safety Dataset 2.0. The dataset has a commercially friendly license and is publicly available to permit community analysis and development.

License#

Component

Artifact Type

Artifact Licenses

Llama 3.1 NemoGuard 8B ContentSafety NIM

Container

NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.

Llama Nemotron Safety Guard V2, formerly known as Llama-3.1-NemoGuard-8B-ContentSafety

Model

NVIDIA Community Model License Agreement.

Llama 3.1 Community License Agreement. Built with Llama.