Transformer architecture

As explained in How Large Language Models Work

A transformer is a neural-network architecture that uses attention mechanisms to process relationships among elements in a sequence.

A transformer is a neural-network architecture for processing sequences. It represents tokens as numbers, compares their relationships, and predicts useful outputs. In language models, it predicts tokens rather than literally understanding language or reasoning like a person. section 3.1 section 3.1.1

The basic pipeline has three parts: an embedding layer maps tokens to meaning-bearing vectors; repeated transformer layers relate those vectors; and an output layer converts numerical results into readable words. Position information is added because word order does not arise naturally from token representations. section 3.1.1 section 3.5

Attention supplies the architecture’s flexible way to connect sequence elements:

• Treat a query as what the model is looking for, keys as possible matches, and values as information associated with those matches. section 3.2.2
• Compare every key with a query by similarity, weighting stronger matches more heavily instead of requiring an exact dictionary lookup. section 3.2.2
• Use attention to emphasize relevant information and reduce the influence of distracting information; what matters changes with the available alternatives. section 3.2.2
• Feed previously generated tokens back into the model at each step, then produce probabilities for every possible next token before selecting one. section 3.5

A fuzzy dictionary

A Python dictionary needs an exact key to return a value. A transformer instead compares a query with all available keys and combines their values according to similarity. In next-token prediction, the current token acts as the query and preceding words provide keys. The result is not a guaranteed answer: it is a probability distribution from which a token can be selected, with randomness affecting consistency and creativity. section 3.2.2 section 3.5

Figure 3.1 The basic components of the transformer model, consisting of the embedding layer, multiple transformer layers, and the output layer

Use the architecture diagram to trace tokens through embeddings, multiple transformer layers, and the output layer. section 3.1.1

Transformer variants serve different jobs. Encoder-only models create representations for machine-learning tasks; decoder-only models generate continuations; and encoder-decoder models transform one passage into another, often helping with translation or summarization. Larger transformers can scale efficiently, but they demand more resources, increase prediction time, and may require remote hardware or continuous connectivity. section 3.1 section 4.5

How How Large Language Models Work covers it

How deep it goes

Explains layers, attention, prediction types, and scaling behavior, but stops short of building an LLM from scratch or exposing proprietary details.

Examples

Uses Python dictionaries, preceding words, next-token prediction, translation, summarization, and a component diagram.

What it assumes

Assumes basic coding constructs but teaches transformer vocabulary and mechanics without requiring advanced mathematics.

What you can do after

Evaluate/understand transformer outputs, model variants, sampling behavior, and practical deployment trade-offs.

How it connects

Connects embeddings, positional encoding, attention, autoregressive models, language models, tokenization, and sampling.

liveBookmanning.com

Read How Large Language Models Work on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Learn Generative AI with PyTorchThe internal design and structural organization of a Transformer model built around decoder blocks or self-attention components.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionA transformer is a neural network architecture that uses attention mechanisms to process sequences and model relationships among their elements.
• 

  liveBookmanning.com
  Sutskever's ListA Transformer is a neural network architecture based primarily on attention mechanisms for modeling relationships among sequence elements.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA neural-network architecture based on attention mechanisms, used here as the core architecture for large language models.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)A transformer architecture is a neural-network architecture that uses attention mechanisms to process relationships among elements in a sequence or other structured input.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA Transformer is a neural-network architecture designed to process sets or sequences using attention-based contextual representations.
• 

  liveBookmanning.com
  AI-Powered SearchA transformer is a neural-network architecture that models relationships among sequence elements using attention and can encode and decode representations.
• 

  liveBookmanning.com
  Transformers in ActionA transformer is a neural network architecture that processes sequential and other structured data using attention mechanisms.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA neural network architecture for sequence modeling and content understanding based on attention rather than recurrence or convolution.
• 

  liveBookmanning.com
  LLMs in ProductionA transformer architecture is a neural-network architecture that models sequence relationships primarily through attention rather than recurrence or convolution.
• 

  liveBookmanning.com
  Grokking AI ApplicationsA transformer is a neural-network architecture for sequential data that uses attention to relate elements of an input sequence.
• 

  liveBookmanning.com
  The AI Pocket BookA neural network architecture that contextualizes each token using surrounding tokens rather than compressing the whole prompt into one summary vector.
• 

  liveBookmanning.com
  Time Series Forecasting Using Foundation ModelsA neural-network architecture built from stacked attention and feed-forward processing components, typically organized into encoder and decoder parts.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthA transformer model is a neural network architecture that uses attention-based mechanisms to model contextual relationships in structured sequences or other data.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA sequence model built from positional encoding and multiheaded attention, used here as the standard original design for NLP and other tasks.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionThe Transformer is a neural-network architecture based primarily on attention mechanisms for processing sequences and modeling context.
• 

  liveBookmanning.com
  Hugging Face in ActionThe Transformer architecture is a neural-network architecture based on attention mechanisms for processing sequences and other structured inputs.
• 

  liveBookmanning.com
  Domain-Specific Small Language ModelsA neural network architecture for sequence modeling built around self-attention and parallel processing, underlying both large and small language models.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionA transformer is a neural-network architecture for sequence modeling that uses attention, especially self-attention, rather than recurrence.
• 

  liveBookmanning.com
  Build AI-Enhanced Web AppsA transformer model is a neural-network architecture that uses attention mechanisms to model contextual relationships in sequence data.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)a neural network architecture based on self-attention mechanisms that enables processing of sequential data and underpins many large language models.
• 

  liveBookmanning.com
  Build a Website with ChatGPTA transformer is a neural-network architecture that processes sequences using attention mechanisms to model relationships among their components.
• 

  liveBookmanning.com
  Data Analysis with LLMsThe Transformer is a neural-network architecture designed to model relationships in sequences, especially sequences with variable-length inputs or outputs.
• 

  liveBookmanning.com
  Generative AI in ActionThe Transformer architecture is a neural-network architecture based primarily on attention mechanisms for processing sequences.
• 

  liveBookmanning.com
  Coding with AIA Transformer is a neural-network architecture that processes sequence elements using attention and can process them in parallel.
• 

  liveBookmanning.com
  Optimization Algorithms: AI techniques for design, planning, and control problemsA transformer architecture is a neural-network architecture that processes sequences primarily through attention mechanisms rather than recurrence.
• 

  liveBookmanning.com
  Essential GraphRAGA transformer architecture is a neural-network architecture that processes sequences using attention-based representations and supports efficient language modeling.

Compare how 28 books explain transformer architecture →

Related concepts

• attentionuses · Attention is a neural-network mechanism that computes input-dependent weights to combine information according to its relevance to a computation.
• encoderhas part · An encoder is a component that transforms input data into an encoded representation for subsequent processing, reconstruction, comparison, or transmission.
• decodehas part · Decoding is the process of transforming an encoded or internal representation into an interpretable or target-form output.
• Vision Transformerincludes · A Vision Transformer is a Transformer-based neural-network architecture that processes images as sequences of tokenized regions using attention.
• model architecturekind of · The structural organization of a computational system’s components, relationships, and operations that determines how it processes information or behaves.
• GPT-2includes · GPT-2 is a family of autoregressive, decoder-only Transformer language models developed by OpenAI that generate text by predicting successive tokens from preceding context.

This explainer was generated by Manning's knowledge graph from the text of How Large Language Models Work. The section links point to the parts of the book it draws on.