1 result found Sort:

sail-sg
Attention-Sink sail-sg
1
36
mit
5
[ATTRIB @ NeurIPS 2024 Oral] When Attention Sink Emerges in Language Models: An Empirical View
attention-sink language-model attention-mechanism large-language-models
Created 2024-10-13
6 commits to main branch, last one 2 months ago