karpathy/nanochat
The best ChatGPT that $100 can buy.
What it is
nanochat is the simplest experimental harness for training LLMs. It is designed to run on a single GPU node, the code is minimal/hackable, and it covers all major LLM stages including tokenization, pretraining, finetuning, evaluation, and inference. For example, you can train your own GPT-2 capability LLM (which cost $43,000 to train in 2019) for only $48 (2 hours of 8XH100 GPU node) and then talk to it over a simple CLI. On a spot instance, the total cost can be closer to ~$15. More generally, nanochat is configured out of the box to train an entire miniseries of compute-optimal models by setting one single complexity dial: --depth, the number of layers in the GPT transformer model (GPT-2…
When to use it
Reach for nanochat when you need to call, serve, run locally, fine-tune or chat with a language model — it's written in Python and fits stacks tagged openai.
