ml.lab
Python sleeps until you run code

The suite

Where this goes

Part 1 builds the foundations and the first real sequence models. Each later part builds on it, ending with the engineering between a trained model and a product. The first lesson, The big picture, gives a plain-language map of all of it today.

  1. 01

    From matrices to memory

    The math refresher and the first real models: vectors, matrices, eigenvalues, Jacobians, backpropagation, recurrent networks and LSTMs trained in your browser.

    • Linear algebra
    • Calculus for learning
    • Backpropagation
    • RNNs
    • LSTMs
    Available now
  2. 02

    Attention and transformers

    Build a small GPT: tokenization, embeddings and positions, self-attention, the transformer block, training, sampling and the KV cache.

    • BPE tokenization
    • Self-attention
    • Transformer blocks
    • A tiny GPT
    • Inference
    Planned
  3. 03

    Pretraining at scale

    What changes when the model and data get large: data pipelines, scaling laws, optimizers and schedules, mixed precision and parallelism.

    • Data
    • Scaling laws
    • AdamW and schedules
    • Mixed precision
    • Parallelism
    Planned
  4. 04

    Post-training

    Turning a base model into an assistant: supervised fine-tuning, reward models, RLHF and DPO, reinforcement learning with verifiable rewards, LoRA and distillation.

    • SFT
    • Reward models
    • RLHF and DPO
    • RL with verifiable rewards
    • LoRA
    Planned
  5. 05

    Vision

    Convolution, CNNs, detection from sliding windows to the R-CNN family, segmentation with FCN, U-Net and Mask R-CNN, vision transformers and CLIP.

    • Convolution
    • Detection
    • Segmentation
    • ViT
    • CLIP
    Planned
  6. 06

    Models in products

    Inference, quantization, retrieval, evaluation and agents: the engineering between a trained model and something a customer relies on.

    • Serving
    • Quantization
    • Retrieval
    • Evals
    • Agents
    Planned