試験
通常
試験時間: 00:00問題時間: 00:00
問題一覧
問題 5 / 65
Which method is suitable for reducing a model's computation and size while maintaining performance when deploying to edge devices?
①Retrain with additional data.
②Use knowledge distillation to transfer knowledge from a large teacher model to a smaller model.
③Compress solely by improving the prompt.
④Use a large-scale model as-is for transfer learning.
⑤Combine multiple models in an ensemble.