Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

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

The best ChatGPT that $100 can buy.

Extremely fast Query Engine for DataFrames, written in Rust

Download market data from Yahoo! Finance's API

Scrape papers from OpenReview using OpenReview API

A TTS model capable of generating ultra-realistic dialogue in one pass.

Python SEC EDGAR Filings API. Over 18 million filings, all 150 filing types supported. Query, full-text search and real-time stream API. Convert XBRL-to-JSON and access standardized financial state…

Documenting large text datasets 🖼️ 📚

What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasets

Implementation of Rank-biased Overlap

A Conversational Speech Generation Model

Collection of LLM completions for reasoning-gym task datasets

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

A comprehensive repository of reasoning tasks for LLMs (and beyond)

Code for "Is There a Replication Crisis in Finance" by Jensen, Kelly and Pedersen (2023)

Fully open reproduction of DeepSeek-R1

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Extracting spatial and temporal world models from LLMs

An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"

Training Sparse Autoencoders on Language Models

Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.