一句话:将代码预训练模型压缩至约3 MB,以降低内存与运行开销并改善个人设备部署体验。
大型代码预训练模型在多种代码处理任务上取得显著效果,但其数百 MB 的内存占用和较慢的个人设备运行速度,阻碍了它们在软件开发者日常工作流中的广泛采用。本文针对模型部署困难和用户体验下降的问题,研究将代码预训练模型压缩到约 3 MB。标题所提示的关键结果是模型体积大幅缩小,从而有望降低内存开销并提升个人设备上的运行效率。摘要没有给出具体压缩技术、目标任务或精度损失等评估细节,因此其评估主要关注模型规模以及部署可用性。
Although large pre-trained models of code have delivered significant advancements in various code processing tasks, there is an impediment to the wide and fluent adoption of these powerful models in software developers’ daily workflow: these large models consume hundreds of megabytes of memory and run slowly on personal devices, which causes problems in model deployment and greatly degrades the user experience.