Stabilizing Transformer Training by Preventing Attention Entropy Collapse.
Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin, Dan Busbridge, Jason Ramapuram, Yizhe Zhang, Jiatao Gu, Joshua M. Susskind
Browse the full ICML paper archive.
Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin, Dan Busbridge, Jason Ramapuram, Yizhe Zhang, Jiatao Gu, Joshua M. Susskind
Browse the full ICML paper archive.