Convert any PDF into a podcast episode!

Sparse autoencoders

Minimal and clean examples of machine learning algorithms implementations

DSPy: The framework for programming—not prompting—foundation models

LinearBoost Classifier is a rapid and accurate classification algorithm that builds upon a very fast, linear classifier.

Distribute and run LLMs with a single file.

llama3 implementation one matrix multiplication at a time

Solve puzzles. Improve your pytorch.

Implementation of Alpha Fold 3 from the paper: "Accurate structure prediction of biomolecular interactions with AlphaFold3" in PyTorch

Kolmogorov Arnold Networks

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Machine Learning Engineering Open Book

A playbook for systematically maximizing the performance of deep learning models.

A JAX research toolkit for building, editing, and visualizing neural networks.

The nnsight package enables interpreting and manipulating the internals of deep learned models.

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

Opinionated cookiecutter template for creating a new Python library

Print-friendly, minimalist CV page

The OS for your personal finances

Calculates various features from time series data. Python implementation of the R package tsfeatures.

Lightning ⚡️ fast forecasting with statistical and econometric models.

Python programs, usually short, of considerable difficulty, to perfect particular skills.

Prompt design using JSX.

The Data Science Lifecycle Process is a process for taking data science teams from Idea to Value repeatedly and sustainably. The process is documented in this repo.