# Start a Fine-tune

Once you have a dataset with enough examples (see [Quantity & Quality of Data](/guides/build-a-dataset/quantity-and-quality-of-data.md)) and have connected a [model provider](/key-concepts/model-providers.md) that supports fine-tuning, you are ready to fine-tune a model.

To start a fine-tune, go to Models, press the + button, and choose "Start a fine-tune."

<figure><img src="/files/e9Com55s9U6ON5dVYJ6K" alt=""><figcaption></figcaption></figure>

On the next screen, you can select your [template](/key-concepts/templates.md) and [model provider](/key-concepts/model-providers.md). You can also see the token counts and estimated time and/or cost if available.

{% hint style="info" %}
For most fine-tuning jobs, the template should be very minimal. You do not need to include a lengthy instructional prompt, although in small datasets a very short prompt or semantic labels for your field references can help cue desired behavior.
{% endhint %}

In the next section, we'll discuss common fine-tuning hyperparameters and how to set them.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.entrypointai.com/guides/fine-tune-a-model/start-a-fine-tune.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.