🏅 Collection of Kaggle Solutions and Ideas 🏅

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

LLM inference in C/C++

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Automatically collect and visualize usage statistics in Ubuntu/OSX environments.

nanoGPT style version of Llama 3.1

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Official implementation of "DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning" in ICML'24

Sorting Google Scholar search results based on the number of citations

awesome confidence calibration paper list

Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world application of a neural net trained with backpropagation.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

An autoregressive character-level language model for making more things

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Neural Networks: Zero to Hero

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

LLM101n: Let's build a Storyteller

"Probabilistic Machine Learning" - a book series by Kevin Murphy

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Inference Llama 2 in one file of pure C

LLM training in simple, raw C/CUDA

Interactive Visual Machine Learning Demos.

Single Hyperspectral Image Denoising, Inpainting, Super-Resolution

A Deep Learning based project for colorizing and restoring old images (and video!)

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Docker Cheat Sheet