Skip to main content
7BBusyBoss

Axolotl

by axolotl-ai-cloud

Config-driven LLM fine-tuning. YAML in, fine-tuned model out — abstracts away the boilerplate of every major training stack.

⭐ 9,000 stars🍴 0 forksPythonfine-tuningconfig-drivenmulti-gpu
Start hereRead the setup guide →Install steps and usage, straight from the docs.Source codeDownload ZIPLatest commit on default branch.SourceView on GitHubgithub.com/axolotl-ai-cloud/axolotl
Project site: axolotl.ai

About Axolotl

Axolotl is a Python open-source fine-tuning project by axolotl-ai-cloud. Config-driven LLM fine-tuning. YAML in, fine-tuned model out — abstracts away the boilerplate of every major training stack. With 9,000 GitHub stars and 0forks, it's one of the Fine-Tuning tools worth knowing. You can download the source, browse it on GitHub, or read the full setup guide in the README below.

From the project README

Axolotl

A Free and Open Source LLM Fine-tuning Framework

GitHub License tests codecov Releases

This is an excerpt from the project's own README, quoted here for reference. Read the full README on GitHub →

Axolotl — FAQ

What is Axolotl?

Config-driven LLM fine-tuning. YAML in, fine-tuned model out — abstracts away the boilerplate of every major training stack.

Is Axolotl free to use?

Yes. Axolotl is open-source and free. You can browse the source on GitHub or download it here at no cost — no signup required.

How do I install and run Axolotl?

Download the latest source as a ZIP from GitHub (or clone the main branch), then follow the setup steps in the README below.

What language is Axolotl written in?

Axolotl is primarily written in Python.

How popular is Axolotl?

Axolotl has 9,000 stars and 0 forks on GitHub — a useful signal of how actively it's maintained and trusted by developers.

More Fine-Tuning skills

See all Fine-Tuning →
LLaMA Factory⭐ 38,000

Easy and efficient LLM fine-tuning. Web UI, supports 100+ models and every major technique (LoRA, QLoRA, full, DPO).

Unsloth⭐ 22,000

Fine-tune Llama, Mistral, Gemma 2-5x faster with 80% less memory. Drop-in LoRA + QLoRA training.