Concept
Adapter
An adapter is a small set of trainable parameters inserted into a large pretrained model so you can specialize it for a new task without updating the original weights. Think of it like a diff layer on top of a frozen base model, except the diff is learned rather than…
The rest of “Adapter” 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→