A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yan, Zhang, Tianyi, Li, Zechuan, Han, Soyeon Caren
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.02659