> ## Documentation Index
> Fetch the complete documentation index at: https://docs.literalai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Fine-tuning

> Fine-tune your LLM models to improve performance and reduce costs.

Fine-tuning is the process of training an existing Machine Learning model -- LLM here -- on a custom dataset of input/output examples.

## How it works

### Fine-tuning

LLM providers offer fine-tuning as a service, you simply need to provide the trainign data in the right format.
Behind the scenes, the LLM provider freezes the original model's weights and slides in a few layers of trainable weights (LoRA).

Training happens on the LLM provider's infrastructure and the loss function (cross-entropy) is the metric optimized against.
Best practices are to pass in a training and a validation dataset to ensure your fine-tuned model is not overfitting.

<Tip>
  Do not forget to test your final model beyond the next-token prediction task: you should set benchmarks to evaluate the performance of the
  fine-tuned model on the real-world task you plan to use it on: summary, extraction, tone of voice, RAG, etc.
</Tip>

### Dataset export

Literal AI simplifies the creation of training datasets with `Generation` datasets.

You can build `Generation` datasets from your logs, or from your annotation queues: the format is compatible with the OpenAI fine-tuning format.

To download your datasets as JSONL (JSON Lines) files, you can use the `Download` button on the dataset page:

<Frame caption="Download Generation Dataset">
  <img src="https://mintcdn.com/chainlit-5/SattO4WPsa_7pLDy/images/download-jsonl.gif?s=557f25a951c9267ad7e964d13ed191b6" alt="Download Generation Dataset" width="1497" height="760" data-path="images/download-jsonl.gif" />
</Frame>

## Distillation

Often-times, the hard part is to come up with the right dataset to train on. It should be:

* high quality
* representative of the real-world task you want to use the model on
* large enough to train a good model

From production logs generated with a high-performance LLM, you can automatically generate mulitple quality samples of input/output messages.

Once you have built a stable enough dataset, you can reduce costs by fine-tuning a smaller model on the data you gathered.

This is what is called **distillation**: you are distilling the knowledge of the original model into a smaller model.