# What is Axolotl?

Axolotl is an open-source tool for fine-tuning language models that describes a whole training run in one YAML config. It is built on the Hugging Face libraries and supports LoRA, QLoRA and full fine-tuning.

## What it does

Axolotl wraps the Hugging Face training stack ([Transformers](/glossary/hugging-face-transformers), PEFT, Accelerate) behind a config file. You name the base model, the datasets, the adapter settings and the hyperparameters in YAML, and start the run with one command:

```bash
axolotl train examples/llama-3/lora-1b.yml
```

Axolotl handles dataset loading and formatting, tokenization and the training loop. It supports [LoRA](/glossary/lora), [QLoRA](/glossary/qlora) and full fine-tuning, on one GPU or several, and reads the common instruction and chat dataset formats. The output is a Hugging Face checkpoint or adapter.

## When to use it

Axolotl fits when you want a whole fine-tuning run defined in one config, with example configs to start from.

## Axolotl and Halo

Both are driven by a YAML config, and both sit on the Hugging Face stack. Reach for Halo when the run is one of these:

- a [mixture-of-experts](/glossary/mixture-of-experts) model that has to be split across GPUs with [expert parallelism](/glossary/expert-parallelism),
- online reinforcement learning at multi-GPU scale, with rollout servers and weight sync.

The [quickstart](/halo/docs/quickstart) shows a first Halo run.

