Home

Track

From Scratch

Goal: Build tiny nets, tokenizers, and a GPT by hand, in code, instead of only watching the architecture explained.

Prereqs: Deep Learning and Python for ML.

Status: done

Work through the steps in order. Bold links open YouTube.

Step Concept YouTube Read
1 Autograd engine from scratch Karpathy — The spelled-out intro to neural networks and backpropagation: building micrograd  
2 A net from raw NumPy, no autograd Samson Zhang — Building a neural network FROM SCRATCH (no Tensorflow/Pytorch, just numpy & math)  
3 MLP language model from scratch Karpathy — Building makemore Part 2: MLP  
4 A deeper sequence model from scratch Karpathy — Building makemore Part 5: Building a WaveNet  
5 BPE tokenizer from scratch   minbpe — minimal byte-pair encoding implementation
6 Train a GPT yourself   nanoGPT — the simplest repo for training a GPT
7 A GPT in raw C/CUDA   llm.c — training GPT-2 without PyTorch or Python

Found a broken link or an unclear step? Report a problem with this track.