Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nielsen, Jacob, Schneider-Kamp, Peter, Galke, Lukas
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.11895