AWS AI Practitioner
A company is evaluating customization options for a foundation model (FM). Match each data scenario to the appropriate customization technique. Drag and drop the correct customization technique next to the data scenario it describes.
Explicación
Fine-tuning uses labeled data (input-output pairs) to specialize a model for a specific task. Continued pre-training uses unlabeled data to extend a model's knowledge in a domain. Distillation transfers knowledge from a large teacher model to a smaller student model.