> See the full index of documentation pages at https://docs.zettabyte.com/llms.txt.

# Fine-tune and deploy

> Adapt an existing model to your data, then deploy the result as an inference endpoint.

Source: https://docs.zettabyte.com/docs/tutorials/fine-tune-and-deploy

Last updated: 2026-07-20

This tutorial will connect the fine-tuning flow to deploying and serving the fine-tuned model as an endpoint.

> [!NOTE]
> **Coming soon**
> This recipe is being prepared. It will cover the goal, prerequisites, copy-paste commands, expected output, and cleanup (releasing resources) for fine-tuning a model and deploying it. It is published once the command sequence has been tested end to end.