# What is fine-tuning?

Fine-tuning is training a pretrained model further on your own data so that it behaves the way a task needs. It changes the model's weights, which is what sets it apart from prompting.

## How it works

A pretrained model already knows language. Fine-tuning runs more training steps on a much smaller dataset: the model predicts, a loss measures the error against your examples, and gradients update the weights. The run is short next to [pre-training](/glossary/pre-training), so the model keeps most of what it knows and shifts toward the new data.

What gets updated is a choice:

- **[Full fine-tuning](/glossary/full-fine-tuning)** updates every weight.
- **[LoRA](/glossary/lora)** (low-rank adaptation) and other parameter-efficient methods ([PEFT](/glossary/peft)) freeze the model and train a small set of added weights.

## What it is for

- A fixed output format, tone or style.
- A narrow task where a small model has to match a large one.
- A domain with its own vocabulary, such as law or medicine.
- Behavior that a prompt cannot hold reliably, or a prompt too long to send on every call.

Fine-tuning does not keep facts current. Retrieval-augmented generation (RAG) does: see [fine-tuning vs RAG](/glossary/fine-tuning-vs-rag).

## In Halo

[Halo](/halo) is our open-source framework for post-training open models, from supervised fine-tuning to reinforcement learning. One command starts a LoRA run on one GPU:

```bash
halo launch sft examples/sft/qwen3/qwen3-4b-ultrachat-lora.yaml
```

The [quickstart](/halo/docs/quickstart) goes from a running container to a finished run.

