Axolotl
Post-train and fine-tune various AI models with ease on diverse hardware setups.
Why consider Axolotl?
Axolotl is a popular open-source fine-tuning and post-training framework for LLMs written in Python. It supports LoRA, QLoRA, full parameter fine-tuning, DPO, and PPO alignments across Llama 3, Mistral, and Gemma models using simple YAML configuration files.
Learn Axolotl by building
Practical setup notes, real use cases, and copy-ready examples in one focused guide.
In this guide2 sections
Overview of Axolotl
Axolotl streamlines fine-tuning pipelines with support for Flash Attention 2, DeepSpeed ZeRO, and FSDP.
Quickstart
pip install -e .accelerate launch -m axolotl.cli.train config.yamlAxolotl is licensed under the Apache License Version 2.0.
Related tools
More options with a similar category or technology profile.
diskus
Minimal, fast alternative to du -sh written in Rust using multi-threaded directory traversal.
peco
Simplistic interactive filtering tool for Unix pipelines, process lists, and file trees.
Dapr CLI
Command-line tool for managing Dapr distributed application runtime environments and sidecars.
Freeze
Generate beautiful image screenshots and SVGs of code snippets and terminal outputs.