epochs

Build it yourself.

12 hands-on projects, from a tiny language model to fine-tuning and shipping your own API. Each is broken into steps with working code and a check to tell you it's right, and every code step has been run and tested.

Beginner2–3 hours · Free

A tiny language model

Generate new names by predicting one letter at a time, the same idea as an LLM predicting tokens.

Uses: Tokens and embeddings, Transformers4 steps
Beginner2–3 hours · Free

Build a tokenizer

Teach a program to split text into tokens the way GPT-style models do, by learning merges from a book.

Uses: Tokens and embeddings, ML from scratch5 steps
Beginner3–4 hours · Pro

Build a spam filter

Train logistic regression from scratch on real text messages, then decide how strict the filter should be.

Uses: Classical machine learning, Python and maths toolkit5 steps
Beginner2–3 hours · Pro

A search engine for your notes

Build BM25, the keyword search behind most search boxes, and point it at your own notes.

Uses: Search and retrieval5 steps
Beginner2 hours · Pro

An A/B test analyser

Write the maths behind an experiment dashboard: significance, confidence intervals, sample size and a bug check.

Uses: Statistics and experiments4 steps
Intermediate3–5 hours · Pro

A neural network in NumPy

Write the forward pass, backpropagation and training loop yourself, and prove your gradients are right.

Uses: Neural networks, Python and maths toolkit5 steps
Intermediate3–4 hours · Pro

An evaluation harness

Build the tool every AI team needs: run a fixed test set, see what passed, and know whether a change really helped.

Uses: Evaluation, Prompting and context5 steps
Intermediate4–6 hours · Pro

Chat with your documents

Build retrieval-augmented generation end to end: chunking, retrieval, a grounded prompt, citations and an evaluation.

Uses: Search and retrieval, Prompting and context, Evaluation6 steps
Advanced4–6 hours · Pro

A tool-using agent

Build the agent loop yourself: tools, a step limit, a trace of every action, and tests that don't need an API.

Uses: Agents, Prompting and context, Production AI and MLOps5 steps
Intermediate3–4 hours · Pro

Recognise handwriting with PyTorch

Train a small convolutional network that reads handwritten digits, and learn the PyTorch workflow every ML team uses.

Uses: Deep learning in PyTorch, Neural networks5 steps
Advanced3–4 hours · Pro

Fine-tune a language model with LoRA

Teach a real language model a new style by training less than 0.2% of its weights, on a laptop CPU.

Uses: Training and fine-tuning, Deep learning in PyTorch, Tokens and embeddings5 steps
Intermediate2–3 hours · Pro

Put your project online

Turn the notes search engine into a tested web API, package it with Docker, and give it a public address.

Uses: Production AI and MLOps, Search and retrieval6 steps