Parameter-Efficient Fine-Tuning (PEFT)
A collection of fine-tuning techniques that adapt pre-trained models by modifying only a tiny fraction of parameters.
PEFT techniques freeze the base weights of a pre-trained model and inject small, trainable parameter blocks (adapters). This minimizes storage requirements and training costs while matching the performance of full fine-tuning.
Historical figures and technical concepts for informational purposes only. Not technical, professional, legal, or financial advice. Sources: Official Documentation.