Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Qingyun, Song, Xiaohui, Zhou, Feng, Qin, Zengchang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!