Parameter-efficient fine-tuning in large language models: a survey of methodologies

The large language models, as predicted by scaling law forecasts, have made groundbreaking progress in many fields, particularly in natural language generation tasks, where they have approached or even surpassed human levels. However, the unprecedented scale of their parameters brings significant computational and storage costs. These large language models require substantial computational resources and GPU memory to operate. When adapting large language models to specific downstream tasks, their massive parameter scale poses a significant challenge in fine-tuning on hardware platforms with limited computational power and GPU memory. To address this issue, parameter-efficient fine-tuning (PEFT) offers a…

• NN
  National Natural Science Foundation of China

  Award: U22A6001
• NK
  National Key Research and Development Program of China

  Award: 2023YFE0108600