Training & tuning concept illustration

Training & tuning

Low-rank adaptation

LoRA

A cheap, efficient way to fine-tune a model by training a small number of extra parameters instead of all of them.

In practice

LoRA lets you customize a large model on a single GPU.

Related terms

See what your tokens really cost

Track usage and spend across every model and platform, free.

Image: panumas nikhomkhai on Pexels. Definition free to reuse under CC BY 4.0.