PEFT / LoRA
Hugging Face's parameter-efficient fine-tuning library
Verdict
Essential library for parameter-efficient fine-tuning. LoRA, QLoRA, IA³, and adapters. Reduces trainable params by 99% while maintaining quality. Core dependency of every fine-tuning toolkit.
Other Data & Fine-tuning
- Hugging Face HubProduction
The GitHub of AI — models, datasets, and Spaces in one platform
- Weights & BiasesProduction
ML experiment tracking, model registry, and dataset versioning
- UnslothStable
2× faster LLM fine-tuning with 70% less memory
- AxolotlStable
Easy-to-use fine-tuning toolkit supporting YAML-based configuration
- Scale AIProduction
Enterprise data labelling platform with human-in-the-loop
- Label StudioStable
Open-source data labelling for text, images, audio, and video