ML Workshop

Learn to train models — from a 4-line training loop to fine-tuning LLMs — free, hands-on, on your own machine.

MIT licensed No accounts Runs on CPU or GPU Works offline after setup

Get the course on GitHub →

Why this exists

Good ML education shouldn't cost thousands of dollars or require a cloud subscription. This course runs entirely on the machine you already own — a CPU-only laptop works — and every line of it is MIT-licensed: take it, teach with it, build on it. Even the licensing of every model and dataset is documented honestly, so you learn that part of the craft too.

The five lessons

#LessonYou buildTime
1Tiny net from scratchTensors, autograd, the 5-line training loop — by hand~2 min
2Tiny GPT from scratchTokenizers, attention, a transformer that writes fake Shakespeare~3 min
3Fine-tune DistilBERTA 95%-accuracy sentiment classifier + an overfitting demo~5 min
4LoRA-tune an LLMTurn a 1.7B chat model into a pirate with 0.37% of its parameters~5 min
5Diffusion & style LoRADiffusion from scratch, then teach image models a public-domain art style~15 min

Every lesson is the same five lines — data → forward → loss → backward → step — so by lesson 5, fine-tuning Stable Diffusion feels like coming home.

Made for any machine

GPU ≥12GB: everything, including the FLUX.1-schnell bonus track.
GPU 4–12GB: everything except FLUX training (SD1.5 LoRA trains in ~3GB).
CPU only: lessons 1–3 in full, lesson 4 at smoke-test scale, lesson 5's from-scratch part — plus pre-computed results so you never miss the payoff.

A one-time bootstrap detects your hardware, picks the right PyTorch build (CUDA / ROCm / Apple Silicon / CPU), and downloads the models — showing each license before it downloads anything.

What's coming

Planned free releases: QLoRA & preference tuning (v1.1), inference & deployment (v1.2), RAG & agents (v1.3), more modalities (v1.4). Star the repo to follow along.