Andrej Karpathy
Wrote llama2.c, a dependency-free C program for running Llama 2 models on a personal computer
Andrej Karpathy's site describes an AI researcher and educator who, since 2024, has made educational videos on AI. Karpathy wrote llama2.c, a minimal project that trains Llama 2 architecture models in PyTorch and runs them with a single C file; its README shows small models running on a laptop, explains how to load Meta's Llama 2 models, and adds an int8-quantized variant. Earlier, Karpathy was a founding member and research scientist at OpenAI, Director of AI at Tesla, and returned to OpenAI in 2023–2024.13
Work
llama2.c (external site: github.com)
Wrote the C inference engine, run.c, as a single file with no dependencies, alongside PyTorch training code adapted from Karpathy's earlier nanoGPT. The README walks through running small TinyStories models on an M1 MacBook Air and documents runq.c, which runs int8-quantized checkpoints. The project is MIT-licensed.342
Meta's Llama 2 models in llama2.c
llama2.c's export script converts Meta's Llama 2 checkpoints, including the chat models, and Hugging Face models with the Llama 2 architecture into its own format for the C program. The README notes that float32 inference is practical only up to the 7B model and that the int8 export produces a much smaller checkpoint.3
Earlier roles
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.