TDCSZ327

single-index-ht

Heavy-tailed ESD without gradient noise

early_stopping_double_descent

Code for reproducing figures and results in the paper ``Early stopping in deep networks: Double descent and how to eliminate it''

NJUcheckin

南京大学打卡

pytorch-original-transformer

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

Tianyu_git_test

TDCSZ327/early_stopping_double_descent

Code for reproducing figures and results in the paper ``Early stopping in deep networks: Double descent and how to eliminate it''

TDCSZ327/NJUcheckin

南京大学打卡

TDCSZ327/pytorch-original-transformer

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

TDCSZ327/Tianyu_git_test