Login / Signup
Scalable and Efficient MoE Training for Multitask Multilingual Models.
Young Jin Kim
Ammar Ahmad Awan
Alexandre Muzio
Andrés Felipe Cruz-Salinas
Liyang Lu
Amr Hendy
Samyam Rajbhandari
Yuxiong He
Hany Hassan Awadalla
Published in:
CoRR (2021)
Keyphrases
</>
multi task
classification models
structured prediction
multitask learning
neural network
machine learning
prior knowledge
image features
multi class
learning models