Axolotl

Open-source LLM fine-tuning framework — LoRA, QLoRA, and full fine-tuning for Llama, Mistral, and more

Axolotl is an open-source Python framework for fine-tuning large language models. It supports LoRA, QLoRA, full fine-tuning, RLHF, and DPO training for Llama 3, Mistral, Mixtral, Phi, Falcon, and other models — configured via simple YAML files. Used extensively in the open-source AI community for creating specialized models and improving base models.

Key specs

8,000 GitHub stars source

as of 2026-03-27