Rohith-Rongali's Stars
FlorentinGuth/Rainbow
Code to reproduce experiments in "A Rainbow in Deep Network Black Boxes".
KellerJordan/modded-nanogpt
NanoGPT (124M) quality in 2.67B tokens
dyunis/spectral_dynamics
Code for "Approaching Deep Learning through the Spectral Dynamics of Weights"
pytorch-labs/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
amack315/unsupervised-steering-vectors
facebookresearch/luckmatters
Understanding Training Dynamics of Deep ReLU Networks
chengxiang/LinearTransformer
Pytorch code for experiments on Linear Transformers
pcsl-epfl/hierarchy-learning
Learning a hierarchical model of data with neural networks.
benedekrozemberczki/awesome-decision-tree-papers
A collection of research papers on decision, classification and regression trees with implementations.
lmarena/copilot-arena
SamLynnEvans/Transformer
Transformer seq2seq model, program that can build a language translator from parallel corpus
gpu-mode/awesomeMLSys
An ML Systems Onboarding list
dmarx/anthology-of-modern-ml
Collection of important articles to be treated as a textbook
nmallinar/rfm-grokking
Grokking modular arithmetic with recursive feature machines
patrick-kidger/lineax
Linear solvers in JAX and Equinox. https://docs.kidger.site/lineax
gregorbachmann/Next-Token-Failures
fbach2000/Learning_Theory_from_First_Principles
Python & Matlab code for the figures from the book "Learning Theory from First Principles" by Francis Bach
googlecolab/colabtools
Python libraries for Google Colaboratory
f0uriest/interpax
Interpolation and function approximation with JAX
google-deepmind/nanodo
aaronpmishkin/experiment_utils
Utilities for running optimization and machine learning experiments.
probabilisticai/nordic-probai-2024
Materials of the Nordic Probabilistic AI School 2024.
rajatvd/gifify
rajatvd/sorcerun
Tool to help manage and log computational experiments.
Tsili42/parity-nn
borchero/pycave
Traditional Machine Learning Models for Large-Scale Datasets in PyTorch.
autodiff/autodiff
automatic differentiation made easier for C++
revalo/iceberg
A compositional diagramming and animation library as an eDSL in Python
srush/Tensor-Puzzles-Penzai
pcsl-epfl/regressionsphere
Train a neural network in feature and lazy regimes on a regression task defined on the hyper-sphere.