# Workshop

> Workshop - Upload model artifacts to create, test, and deploy custom models to a centralized model
> management and deployment hub.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-06T18:17:10.046815+00:00` (UTC).

## Primary page

- [Workshop](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/index.html): Full documentation for this topic (HTML).

## Related documentation

- [NextGen UI documentation](https://docs.datarobot.com/en/docs/workbench/index.html): Linked from this page.
- [Registry](https://docs.datarobot.com/en/docs/workbench/nxt-registry/index.html): Linked from this page.
- [DataRobot Model Runner](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/custom-model-drum.html): Linked from this page.
- [custom model assembly guidelines](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/index.html): Linked from this page.
- [Create custom models](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-create-custom-model.html): Linked from this page.
- [View and manage custom models](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-view-manage-custom-models.html): Linked from this page.
- [Define custom model runtime parameters](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/custom-model-runtime-parameters.html): Linked from this page.
- [Test custom models in DataRobot](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-test-custom-model.html): Linked from this page.
- [Add custom model versions](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-custom-model-versions.html): Linked from this page.
- [View and manage a custom model's environment](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-view-manage-model-env.html): Linked from this page.
- [Create custom model proxies for external models](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-ext-model-proxy.html): Linked from this page.
- [Register a custom model](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-register-cus-models.html): Linked from this page.
- [Configure evaluation and moderation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-configure-evaluation-moderation.html): Linked from this page.
- [Use NVIDIA NeMo Guardrails with moderation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-configure-nvidia-nim-evaluation-moderation.html): Linked from this page.
- [Deploy LLMs from the Hugging Face Hub](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-open-source-textgen-template.html): Linked from this page.
- [make predictions via the API](https://docs.datarobot.com/en/docs/api/reference/predapi/legacy-predapi/dr-predapi.html): Linked from this page.
- [monitor your deployment](https://docs.datarobot.com/en/docs/classic-ui/mlops/monitor/index.html): Linked from this page.

## Documentation content

The workshop allows you to upload model artifacts to create, test, and deploy custom models to a centralized model management and deployment hub. Custom models are pre-trained, user-defined models that support most of DataRobot's MLOps features. DataRobot supports custom models built in a variety of languages, including Python, R, and Java. If you've created a model outside of DataRobot and want to upload your model to DataRobot, define the model content and the model environment in the workshop.

**Q: What are custom models?**

Custom models are not custom DataRobot models. They are user-defined models created outside of DataRobot and assembled in the workshop for access to deployment, monitoring, and governance. To support the local development of the models you want to bring into DataRobot through the workshop, the [DataRobot Model Runner](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/custom-model-drum.html) provides you with tools to locally assemble, debug, test, and run the model before assembly in DataRobot. Before adding a custom model to the workshop, DataRobot recommends you reference the [custom model assembly guidelines](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/index.html) for building a custom model to upload to the workshop.

The following topics describe how to manage custom model artifacts in DataRobot:

| Topic | Description |
| --- | --- |
| Create custom models | Create custom models in the workshop. |
| View and manage custom models | View, share, and delete custom models in the workshop. |
| Define custom model runtime parameters | Add runtime parameters to a custom model through the model metadata, making your custom model code easier to reuse. |
| Test custom models in DataRobot | Test custom models in the workshop. |
| Add custom model versions | Create a new version of the model after updating the file contents or settings. |
| View and manage a custom model's environment | Manage the custom model environment defined for a custom model version and view environment information. |
| Create custom model proxies for external models | Create custom model proxies for external models in the workshop. |
| Register a custom model | Add a custom model from the workshop to Registry. |
| Configure evaluation and moderation | (Premium feature) Configure evaluation and moderation guardrails for a custom text generation model in the workshop. |
| Use NVIDIA NeMo Guardrails with moderation | (Premium feature) Connect NVIDIA NeMo Guardrails to deployed text generation models to guard against off-topic discussions, unsafe content, and jailbreaking attempts. |
| Deploy LLMs from the Hugging Face Hub | (Premium feature) Create and deploy open source LLMs from the Hugging Face Hub using a vLLM environment. |

Once deployed to a prediction server managed by DataRobot, you can [make predictions via the API](https://docs.datarobot.com/en/docs/api/reference/predapi/legacy-predapi/dr-predapi.html) and [monitor your deployment](https://docs.datarobot.com/en/docs/classic-ui/mlops/monitor/index.html).