nanochat: Train Your Own GPT-2 Grade ChatGPT in About Two Hours
nanochat trains a ChatGPT-style model from scratch, tokenizer to chat, on a single 8XH100 node. The GPT-2 speedrun record is 1.65 hours, about 1,000 times cheaper than GPT-2 cost in 2019. Here is how it works, what a run really costs, and how to try it. What Is nanochat? nanochat is Andrej Karpathy…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-06 07:33 · DEV Community — Machine Learning
nanochat: Train Your Own GPT-2 Grade ChatGPT in About Two Hours