Axolotl is a free, open-source tool for fine-tuning and post-training open language models, driven by a single configuration file.
In plain words
Fine-tuning involves many steps: preparing data, training, evaluating and quantising. Axolotl lets you describe all of them in one YAML file and reuse it. It supports many open models from the Hugging Face Hub, including vision and audio ones, and many methods, from full fine-tuning and LoRA or QLoRA to preference tuning such as DPO and reinforcement learning such as GRPO.
A quick example
Imagine you want a small open model to answer in your company's support style. You write one Axolotl config naming the base model, your dataset and LoRA settings, run training, then reuse that same file to evaluate and quantise the result.
Where you'll meet it
- Fine-tuning open-weight models on your own data.
- Preference and RL post-training experiments.
Related
Sources
- DocsAxolotl documentation, Axolotl AI · read 29 Sept 2026
- DocsAxolotl README, Axolotl AI (GitHub) · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.