Mapping out the "memory" of neural nets with data attribution

A framework for few-shot evaluation of autoregressive language models.

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

NanoGPT speedrun in JAX. Originally at https://nor-git.pages.dev/modded-nanogpt-jax/

The full minitorch student suite.

Repo to hold code and track issues for the collection of permissively licensed data

The user home repository for the Mathematics in Lean tutorial.

Jupyter runtimes on demand

Rust library for OpenAI

Benchmarking LLMs with Challenging Tasks from Real Users

Examples in the MLX framework

A backup of https://gitlab.com/srwalker101/rust-jupyter-client

Python tools for processing data from the Catalog of Copyright Entries

Incomplete Redis client and server implementation using Tokio - for learning purposes only

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Searching Open Library by keywords to return ISBNs

A JavaScript tool to convert mathml string to LaTeX equation string.

The scraper/parser that produces data for TheyWorkForYou, PublicWhip, etc

🦀 Small exercises to get you used to reading and writing Rust code!