Axolotl
by Axolotl OSS · open-source · Last verified 2026-04-24
Axolotl is a flexible open-source fine-tuning framework that wraps Hugging Face's training ecosystem with YAML configuration for simplifying LLM training workflows. It supports LoRA, QLoRA, full fine-tuning, RLHF, and DPO across all major open-weight model families. Axolotl is widely used by the open-source community for reproducible training recipes.
https://github.com/axolotl-ai-cloud/axolotl ↗C
C—Below Average
Adoption: C+Quality: B+Freshness: ACitations: CEngagement: F
Specifications
- License
- Open Source
- Pricing
- open-source
- Capabilities
- Integrations
- Use Cases
- API Available
- No
- SDK Languages
- python
- Deployment
- self-hosted, docker
- Rate Limits
- N/A (self-hosted)
- Data Privacy
- Self-hosted, user-managed; training data stays local
- Tags
- fine-tuning, lora, qlora, dpo, rlhf, yaml-config, open-source
- Added
- 2026-04-24
- Completeness
- 60%
Index Score
44Adoption
50
Quality
70
Freshness
80
Citations
40
Engagement
0