# Fine Tuning

Kiln makes it easy to fine-tune a wide variety of models like GPT-4o, Llama, Mistral, Gemma, and many more. Check out our fine tuning docs to get started:

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Fine Tuning Guide</strong></td><td>Our end-to-end walkthrough of fine-tuning a model in Kiln. Includes generating training data.</td><td><a href="https://2952104390-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FEJ4b8A4QiEQlOGbYkXDX%2Fuploads%2FVQoiH8d5BlA96DRlBZQH%2Ftuning2.png?alt=media&#x26;token=c8c79e9d-5f79-45bd-9c45-9866e6ff8321">tuning2.png</a></td><td><a href="fine-tuning/fine-tuning-guide">fine-tuning-guide</a></td></tr><tr><td><strong>Train a Reasoning Model</strong></td><td>Using a process called distillation, create your own reasoning model.</td><td><a href="https://2952104390-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FEJ4b8A4QiEQlOGbYkXDX%2Fuploads%2FAGjzQqJgCiZHdVi77QTA%2FDistill2.png?alt=media&#x26;token=78e00959-e9e6-463d-91db-9bbfdf289f62">Distill2.png</a></td><td><a href="fine-tuning/guide-train-a-reasoning-model">guide-train-a-reasoning-model</a></td></tr><tr><td><strong>Fine Tune For Tool Use</strong></td><td>Train a model to use a specific set of tools, at the right time, with the right parameters.</td><td><a href="https://2952104390-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FEJ4b8A4QiEQlOGbYkXDX%2Fuploads%2FuiAcq5orkzq3qqyydLOD%2FMCP.png?alt=media&#x26;token=20ff547e-a640-4e17-9864-9b46300fa213">MCP.png</a></td><td><a href="fine-tuning/fine-tuning-for-tool-use">fine-tuning-for-tool-use</a></td></tr></tbody></table>

{% hint style="success" %}
**Before Fine-Tuning, consider using Kiln's** [**Automatic Prompt Optimizer**](https://docs.kiln.tech/docs/prompts/automatic-prompt-optimizer)**.** It has many of the benefits of fine-tuning (automated data driven optimization), while the result is much easier to deploy than a fine-tuned model.
{% endhint %}
