KellerJordan/modded-nanogpt
NanoGPT (124M) in 90 seconds
Repositories
KellerJordan/Muon
Muon is an optimizer for hidden layers in neural networks
KellerJordan/cifar10-airbench
CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
KellerJordan/BatchNorm-adaptation-behavior
The adaptation behavior of BatchNorm is no different than Norm-Free
KellerJordan/Exponentiated-Gradient-PyTorch
EG plus/minus optimizer implemented in PyTorch
KellerJordan/REPAIR
Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair
KellerJordan/ResNet-PyTorch-CIFAR10
PyTorch implementation of residual networks trained on CIFAR-10 dataset (2017)
KellerJordan/CIFAR-cuda
welcome to the learning zone
KellerJordan/Evaluate-CrossMax-Ensemble
An evaluation of the robust accuracy of the CrossMax Ensemble technique (Fort et al., 2024)
KellerJordan/trak
A fast, effective data attribution method for neural networks in PyTorch
KellerJordan/negative-self-influence
neural networks don't minimize loss [caution: probably due to batchnorm]
KellerJordan/tSNE-Animation
Hacking sklearn's t-SNE implementation to animate embedding process
KellerJordan/robustness-featsnotbugs
A replication of "Adversarial Examples Are Not Bugs, They Are Features" https://arxiv.org/abs/1905.02175
KellerJordan/research-airbench
Variant of cifar10-airbench which removes several tricks. Ideal for research
KellerJordan/Algorithms-Practice
Implementations of a few Algorithms and Data Structures in various languages
KellerJordan/cifar10-loader
Fast and easy to use CIFAR-10 dataloader
KellerJordan/top-sgd
Optimization algorithm which fits a ResNet to CIFAR-10 5x faster than SGD / Adam (with terrible generalization)
KellerJordan/Autoencoder-Clustering
Replication of "Auto-encoder Based Data Clustering" Song et al
KellerJordan/jupyter-fork
real oldschool notebook how they did it in the old days with none of that newfangled BS
KellerJordan/gpt-sandbox
KellerJordan/hlb-CIFAR10
Train to 94% on CIFAR-10 in 4.4 seconds on a single A100
KellerJordan/Vector-Playground
Javascript math sandbox from before I knew about matlab
KellerJordan/elastic-airbench
KellerJordan/zf-compiler
KellerJordan/share-data
KellerJordan/MNIST-test
KellerJordan/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
KellerJordan/llm.c
LLM training in simple, raw C/CUDA
KellerJordan/TriMap-PyTorch
Implementation of TriMap dimensionality reduction in PyTorch
KellerJordan/pixelated-features-bugs
Code for training and evaluating the robustness of models using pixelated data