Agent0 Series: Self-Evolving Agents from Zero Data

dLLM: Simple Diffusion Language Modeling

Sky-T1: Train your own O1 preview model within $450

Our library for RL environments + evals

This repository contains the toolkit for replicating results from our technical report.

Quickly get up and running with Event Sourcing and Agentic workflows in Clojure

Agent Builder and Runtime by Docker Engineering

Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.

Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

A community-maintained Python framework for creating mathematical animations.

NanoGPT (124M) in 3 minutes

A version 1.1 of the Alexander Koch low cost robot arm with some small changes.

Efficient Triton Kernels for LLM Training

The RAG Genie, an LLM RAG prototype to test and evaluate your embeddings, chunk splitting strategies using Q&A and evaluations.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

A benchmark to evaluate language models on questions I've previously asked them to solve.

Whisper with Medusa heads

From the Transistor to the Web Browser, a rough outline for a 12 week course

LLM training in simple, raw C/CUDA

Evaluate the accuracy of LLM generated outputs

Inference Llama 2 in one file of pure C

OpenAI chat client desktop app (Windows, MacOS, Linux)

🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…

OpenChat: Advancing Open-source Language Models with Imperfect Data

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

You like pytorch? You like micrograd? You love tinygrad! ❤️

LLM inference in C/C++

Sim provides a discrete event simulation engine, to facilitate Rust- and npm-based simulation products and projects