Symmetric Dot-Product Attention for Efficient Training of BERT Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Courtois, Martin, Ostendorff, Malte, Hennig, Leonhard, Rehm, Georg
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2406.06366