Parameter-Efficient Fine-Tuning (PEFT) is a set of techniques for adapting large pre-trained models to new tasks without fine-tuning all the model's parameters. Instead, a small number of new parameters are added to the model and trained, or a small subset of the existing parameters are trained.
A collection of techniques for efficiently fine-tuning large models.
Essential for making the fine-tuning of large models accessible to a wider audience.