bbruceyuan/LLMs-Zero-to-Hero
A comprehensive educational series teaching how to build LLMs from scratch, following the style of Andrej Karpathy's deep learning tutorials.

This repository is a learning resource that teaches Large Language Model fundamentals from zero, guiding learners through building an LLM step by step. It provides a structured curriculum with accompanying Bilibili video tutorials and GPU compute resources for hands-on model training. The series covers the complete pipeline from fundamentals to a working miniLLM, with related demo projects available in a companion repository.
Frequently asked
- What is bbruceyuan/LLMs-Zero-to-Hero?
- A comprehensive educational series teaching how to build LLMs from scratch, following the style of Andrej Karpathy's deep learning tutorials.
- Is LLMs-Zero-to-Hero open source?
- Yes — bbruceyuan/LLMs-Zero-to-Hero is open source, released under the Apache-2.0 license.
- What language is LLMs-Zero-to-Hero written in?
- bbruceyuan/LLMs-Zero-to-Hero is primarily written in Jupyter Notebook.
- How popular is LLMs-Zero-to-Hero?
- bbruceyuan/LLMs-Zero-to-Hero has 2.3k stars on GitHub.
- Where can I find LLMs-Zero-to-Hero?
- bbruceyuan/LLMs-Zero-to-Hero is on GitHub at https://github.com/bbruceyuan/LLMs-Zero-to-Hero.