Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind

Large Language Models (LLMs) have ushered in a new era in Natural Language Processing, but their massive size demands effective compression techniques for practicality. Although numerous model compression techniques have been investigated, they typically rely on a calibration set that overlooks the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-04
Hauptverfasser:	Zeng, Hongchuan, Xu, Hongshen, Chen, Lu, Yu, Kai
Format:	Artikel
Sprache:	eng
Schlagworte:	Brain Calibration Data sampling English language Language Large language models Multilingualism Natural language processing Performance enhancement Sampling methods Surgeons
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!