Tuning is the process of adjusting parameters, hyperparameters, prompts, or model behavior to improve performance on a desired task. It may involve selecting configuration values, fine-tuning a model, or refining inputs without changing the base model weights.
The process of adapting a foundation model to perform specific tasks with greater precision and accuracy. Tuning is achieved by adjusting some or all of the model's parameters or training a model on a dataset that contains examples that replicate the tasks and results that you want. Tuning techniques include full fine-tuning (updates all parameters), parameter-efficient tuning / adapter tuning (updates some parameters), and supervised fine-tuning (trains on labeled input-output pairs).