Skip to content
AI-grafen
Sign in
☰ Menu

The goal E University

Language models in practice

Tokenisation, sampling, instruction models, structured output, hallucinations and Swedish — what you need in order to build with an LLM for real.

Knowledge nodes
70
From zero
about 49 h
Labs
6
See what you already know — no account

The diagnostic removes what you already know, so your path is usually much shorter.

What you can do afterwards

Labs along the way

You write the code. Tests you cannot see decide whether it holds up.

Lab: byte-pair encoding from scratchEa sandbox · about 60 minLab: a neural network in pure NumPy — forward, backprop, gradient checkDa sandbox · about 75 minLab: dot product, norm and cosine similarityDin the browser · about 40 minLab: gradient descent from scratchDin the browser · about 50 minLab: matrix multiplication and one layer of a neural networkDin the browser · about 45 minLab: scaled dot-product attention with a causal maskDa sandbox · about 60 min

The whole path

Everything the goal builds on, grouped by level and in the order it builds on itself. Show on the map

AExplorer4 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
  3. Integer arithmetic and order of operations
  4. Comparing and sorting values
BInvestigator11 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Rule-based systems and machine learning
  4. Source criticism and responsibility in AI use
  5. Fractions, decimals, and percentages
  6. Coordinates: positions on a grid
  7. Negative numbers in everyday life and AI
  8. Training data, features and labels
  9. Classification: how a model sorts information
  10. Generative AI: how it creates content
  11. Language models and probabilities
CBuilder15 knowledge nodes
  1. Functions and coordinate systems
  2. Programming logic — variables, conditions, loops
  3. Python — the basics
  4. Python — lists, loops and dictionaries
  5. Python — strings and text processing
  6. Python — files, CSV and JSON
  7. Statistics — mean, median and spread
  8. Probability — the basics
  9. Linear regression: fitting a straight line to data
  10. Neural networks — the intuition
  11. Prompting — steering a language model
  12. Attention: how words influence each other
  13. Words as points: similar words close together
  14. Variables and algebraic expressions
  15. Powers and roots
DAI developer19 knowledge nodes
  1. Derivatives and optimisation
  2. Loss functions
  3. n-gram language models
  4. Tokenisation
  5. Text preprocessing
  6. Gradient descent
  7. The context window, system prompts and few-shot
  8. Precision, recall, F1 and ROC
  9. The transformer — an overview without formulas
  10. Logarithms
  11. Vectors
  12. Matrices and matrix multiplication
  13. Neural networks — the forward pass with matrices
  14. Backpropagation
  15. Embeddings — words as vectors
  16. Attention
  17. PyTorch — tensors and autograd
  18. Train a neural network in PyTorch
  19. Transformers — the architecture
EUniversity21 knowledge nodes
  1. Byte-pair encoding
  2. Reasoning in language models
  3. Structured output and schemas
  4. Information theory: entropy and KL divergence
  5. Generative models — an overview
  6. BERT and masked language modelling
  7. Encoder–decoder transformers
  8. Multi-head attention in detail
  9. Attention variants: cross, causal, sparse
  10. The KV cache
  11. Language models — training and generation
  12. Multilinguality and Swedish models
  13. Hallucinations — causes and countermeasures
  14. Base against instruction models
  15. Perplexity
  16. Sampling: temperature, top-k, top-p, beam
  17. Summarisation and translation
  18. Language models for code
  19. NLP in Swedish: resources and pitfalls
  20. Text classification with transformers
  21. Information extraction and NER