Minimind: Train a 64M-parameter LLM from scratch in just 2h

jingyaogong · github · 2026-08-31

GitHub project jingyaogong/minimind provides a complete codebase and tutorial to train a small 64M-parameter Large Language Model from scratch in just 2 hours. It is suitable for learning LLM training workflows and principles.

Original post →

More from Research

Research channel →