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
- ArgillaStable
Open-source platform for human feedback and RLHF data curation
- AxolotlStable
Easy-to-use fine-tuning toolkit supporting YAML-based configuration
- DVCStable
Git-based data and model version control for ML projects
- Hugging Face HubProduction
The GitHub of AI — models, datasets, and Spaces in one platform
- Label StudioStable
Open-source data labelling for text, images, audio, and video
- LitGPTExperimental
Lightning AI toolkit for pretraining, fine-tuning, and deploying LLMs