An Empirical Study of Parameter-Efficient Fine-Tuning Methods for Pre-Trained Code Models

Pre-trained code models (e.g. CodeBERT and CodeT5) have demonstrated their code intelligence in various software engineering tasks, such as code summarization. And full fine-tuning has become the typical approach to adapting these models to downstream tasks. However, full fine-tuning these large mod...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE/ACM International Conference on Automated Software Engineering : [proceedings] S. 397 - 408
Hauptverfasser:	Liu, Jiaxing, Sha, Chaofeng, Peng, Xin
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 11.09.2023
Schlagworte:	Adaptation models Codes Computational modeling Costs fine-tuning Memory management parameter-efficient pre-trained code models Training Transfer learning
ISSN:	2643-1572
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!