Concept
Full fine-tuning
Full fine-tuning means updating every weight in a pretrained model during training on your downstream task, as opposed to freezing the base and training a small add-on. It is the original, unqualified sense of "fine-tuning" before parameter-efficient methods (PEFT) like LoRA…
The rest of “Full fine-tuning” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→