sail-sg/Adan
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
Language: Python
#adan #bert_model #convnext #deep_learning #fairseq #mae #optimizer #resnet #timm #transformer_xl #vit
Stars: 158 Issues: 2 Forks: 5
https://github.com/sail-sg/Adan