-
University of British Columbia
- Vancouver, BC
- https://nikola-sur.netlify.app/
Highlights
- Pro
Stars
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
A community-maintained Python framework for creating mathematical animations.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Deep universal probabilistic programming with Python and PyTorch
Code for the manim-generated scenes used in 3blue1brown videos
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
A highly efficient implementation of Gaussian Processes in PyTorch
Copy playlists and liked music from Spotify to YTMusic
Awesome machine learning for combinatorial optimization papers.
Exploratory analysis of Bayesian models with Python
Awesome resources on normalizing flows.
BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.
PMLB: A large, curated repository of benchmark datasets for evaluating supervised machine learning algorithms.
PyTorch implementation of normalizing flow models
Everything you want to know about Google Cloud TPU
Dynamic Nested Sampling package for computing Bayesian posteriors and evidences
Compare two version of an arXiv preprint with a single command.