> This page is for version 1.10.1 (default).
> For other versions, use one of these documentation indexes:
> - 1.10.1 (default): https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.10.1/llms.txt
> - 1.0.0: https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/_mcp/server.

# Llama 3.1 NemoGuard 8B TopicControl NIM

> The microservice serves a GPU-accelerated LLM model for conversational dialog moderation to keep conversations on-topic and build trustworthy LLM applications.

## About the Microservice

The microservice serves a GPU-accelerated LLM model for conversational dialog moderation to keep conversations on-topic and build trustworthy LLM applications.

The model is a dialog moderation model trained by NVIDIA from a Llama 3.1 8B Instruct base model.
The model is trained using the CantTalkAboutThis dataset – a carefully curated collection of 10 thousand dialogue samples – to detect and ensure user interactions are in line with developer-defined guidelines.
The dataset has been released with a commercially friendly license.

In contrast with content moderation models such as Shield Gemma and Llama Guard 3, that rely on a pre-defined taxonomy of harms, this model enables developers to specify their own boundaries regarding allowed and disallowed subjects.
This adaptability makes it a more versatile and general-purpose complement to content moderation models.

## License

| Component                               | Artifact Type                                                                                                      | Artifact Licenses                                                                                                                                                                                                                                                                                 |
| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Llama 3.1 NemoGuard 8B TopicControl NIM | [Container](https://registry.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/llama-3.1-nemoguard-8b-topic-control) | [NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) and the [Product-Specific Terms for NVIDIA AI Products](https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/). |
| Llama Nemotron Topic Guard V1           | [Model](https://registry.ngc.nvidia.com/orgs/nim/teams/nvidia/models/llama-3.1-nemoguard-8b-topic-control)         | [NVIDIA Community Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Built with Llama.                                                     |

## Related Information

* [CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues](https://aclanthology.org/2024.findings-emnlp.713.pdf).

* [CantTalkAboutThis](https://huggingface.co/datasets/nvidia/CantTalkAboutThis-Topic-Control-Dataset) topic-control dataset on Hugging Face Hub.

* The microservice is based on [NVIDIA NIM for LLMs](https://docs.nvidia.com/nim/large-language-models/latest/introduction.html).