Axolotl
Config-driven fine-tuning for open LLMs.
YAML-configured full fine-tuning, LoRA/QLoRA, preference tuning (DPO, GRPO) and multi-GPU training for most open model families.
- Vendor
- Axolotl AI
- Category
- Data & ML platforms
- Pricing
- Open source
- Open source
- Yes
- License
- Apache 2.0
- Platforms
- Python, Linux
- Launched
- 2023
- Website
- axolotl.ai
Features
- LoRA / QLoRA
- DPO & GRPO
- Multi-GPU (FSDP, DeepSpeed)
Best for
- Research
- Local & on-device
More data & ml platforms
- Hugging Face — Hugging Face. The home of open models and datasets.
- Weights & Biases — Weights & Biases. The AI developer platform.
- Unsloth — Unsloth AI. Fine-tune LLMs faster with less memory.
- Scale AI — Scale AI. Data labeling and evaluation for frontier AI.
- TRL — Hugging Face. Post-training library: SFT, DPO, GRPO and RL for LLMs.
- Label Studio — HumanSignal. Open-source data labelling for text, images, audio and LLM outputs.