gradnorm-pytorch

Weight-Decay

Regularization, Neural Network Training Dynamics

ConFIG

Official implementation of Conflict-Free Inverse Gradients Method

the-incredible-pytorch

The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relat...

tf-weightnorm

Examples for TensorFlow Weight Normalization

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

grokfast-pytorch

Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow ...

balanced-loss

Easy to use class balanced cross entropy and focal loss implementation for Pytorch

phgrad

phgrad - Cause there are not enough unusable autograd libraries in python

adamw_bfloat16

AdamW optimizer for bfloat16 models in pytorch 🔥.

egnn-pytorch

Implementation of E(n)-Equivariant Graph Neural Networks, in Pytorch

pytorch_misc

Code snippets created for the PyTorch discussion board

NNG-Pytorch