MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding.
Zayd Muhammad Kawakibi Zuhri, Muhammad Farid Adilazuarda, Ayu Purwarianti, Alham Fikri Aji
Browse the full NAACL paper archive.
Zayd Muhammad Kawakibi Zuhri, Muhammad Farid Adilazuarda, Ayu Purwarianti, Alham Fikri Aji
Browse the full NAACL paper archive.