aka PEFT

Parameter-Efficient Fine-Tuning

A family of methods that fine-tune only a small fraction of a model's parameters (or add small trainable modules) instead of updating all weights, drastically cutting memory and compute costs.

LLMs

BACKLOG · WORK IN PROGRESS

This term is being written.

The metadata and shape of this page are stable, but the body content isn't ready yet. We'll publish it once it meets the bar of teaching something new with worked examples and real tools.

Back to wiki Track progress on GitHub