COPAL: Continual Pruning in Large Language Generative Models

Adapting pre-trained large language models to different domains in natural language processing requires two key considerations: high computational demands and model's inability to continual adaptation. To simultaneously address both issues, this paper presents COPAL (COntinual Pruning in Adapti...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-06
Hauptverfasser:	Malla, Srikanth, Choi, Joon Hee, Choi, Chiho
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation Algorithms Datasets Empirical analysis Large language models Natural language processing Sensitivity analysis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!