DAPE V2: Process Attention Score as Feature Map for Length Extrapolation

DAPE V2: Process Attention Score as Feature Map for Length Extrapolation

7 October 2024

Chuanyang Zheng

Jing Xiong

Jingyao Li

Michael Ng

Xin Jiang

Zhenguo Li

Yu Li

Papers citing "DAPE V2: Process Attention Score as Feature Map for Length Extrapolation"

Title
No papers