The easiest way to run an open model on your own machine: one command downloads and starts it, plus a local REST API and libraries for Python and JavaScript.
All repositories
Open models & inferencekarpathy
llm.c
GPT-2 training in plain C and CUDA, no PyTorch. Shows what happens under the hood while a model learns.
Who it is for
For people who want to understand model training at the lowest level.
How to start
- Download the starter pack:
chmod u+x ./dev/download_starter_pack.sh, then./dev/download_starter_pack.sh. - On CPU build and run:
make train_gpt2; on one GPU:make train_gpt2fp32cuand./train_gpt2fp32cu. - Read the tutorial linked in the tutorial section of the README.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+211Sep 6 — Oct 6
Author's description
LLM training in simple, raw C/CUDA
More in «Open models & inference»
The core library for working with models: one codebase for text, vision, audio and multimodal tasks, for both inference and training. Most new open models ship through it.
A self-hosted ChatGPT-style interface that connects to Ollama and any OpenAI-compatible API. Installs with a single Docker command and runs on your own server.
A C/C++ engine that runs language models on ordinary hardware: laptops, phones, GPU-less servers. Much of local AI, Ollama included, is built on it.
Repository of the large open DeepSeek-V3 mixture-of-experts model: description, benchmark results and run instructions. It showed an open model can stand next to closed ones.
The foundation under most modern neural networks: GPU-accelerated tensors and automatic differentiation, wrapped in ordinary Python. Transformers, Llama and nearly every open model are written on it.