Hundreds of strange attractors

Anthropic's original performance take-home, now open for you to try!

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

Python SQL Parser and Transpiler

Fretboard diagram generator

javascript for rendering abc music notation

Implementation of the AL-RNN architecture for dynamical systems reconstruction and time series forecasting.

Handwritten music image synthesizer for HMR

Production-grade client-side tracing, profiling, and analysis for complex software systems.

tpcds queries for presto

TPC-DS queries

code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

A software library of stochastic streaming algorithms, a.k.a. sketches.

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

Language model alignment-focused deep learning curriculum

Build and publish crates with pyo3, cffi and uniffi bindings as well as rust binaries as python packages

Julia bindings for the Enzyme automatic differentiator

cluster data collected from production clusters in Alibaba for cluster management research

Chronos: Pretrained Models for Time Series Forecasting

A collection of Twitter's anonymized production cache traces.

The repo for HotOS paper "FIFO can be Better than LRU: the Power of Lazy Promotion and Quick Demotion"

A C++11 simulator for a variety of CDN caching policies.

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

A library for efficient similarity search and clustering of dense vectors.

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

Interact with your documents using the power of GPT, 100% privately, no data leaks

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.