adaptation

Definition

Adjusting an already-trained model to a new task, domain, or user. It is the economic foundation of the foundation-model era: adaptation costs orders of magnitude less than training from scratch, so one base model branches into many specialized ones. The term is broader than fine-tuning, covering full-parameter updates as well as parameter-efficient methods like LoRA, adapters, and prompt tuning.

Explainers using this term

• Paper Walkthrough: Normalized Low-Rank Adaptation — Why Normalizing LoRA's Entry Matrix WorksNormalized Low-Rank Adaptation
• A Practical Map of Image Generation — SD, ControlNet, and Applying LoRALoRA: Low-Rank Adaptation of Large Language Models
• Singular Value Decomposition and Low-Rank Approximation — the Math Behind LoRALoRA: Low-Rank Adaptation of Large Language Models