Query

As explained in Learn Generative AI with PyTorch

An attention query is a vector representation of the information sought by an input position, compared with key representations to determine which information to attend to.

In self-attention, a query is a learned projection of an input embedding for a sequence position. Compared with keys, it produces scores that determine how strongly that position attends to the values. section 9.1.1

Library search

Searching for “machine learning in finance” is the query; book titles and descriptions are keys, and recommended books are values. In attention, query-key similarity determines the weights applied to values. section 1.3.1

Figure 9.1 A diagram of the self-attention mechanism. To calculate attention, the input embedding X is first passed through three neural layers with weights, W^Q, W^K, and W^V, respectively. The outputs are query Q, key K, and value V. The scaled attention score is the product of Q and K divided by the square root of the dimension of K, d_k. We apply the softmax function on the scaled attention score to obtain the attention weight. The attention is the product of the attention weight and value V.

Follow the diagram from input embedding X through the query, key, and value projections to attention scores, weights, and the resulting attention. section 9.1.1

How Learn Generative AI with PyTorch covers it

How deep it goes

Traces the query from an input-embedding projection through query-key scoring, softmax weights, and value combination.

Examples

Uses a library search for “machine learning in finance” to illustrate queries, keys, and values.

What it assumes

Introduces tokens, embeddings, and positional encoding before using input embeddings to form queries.

What you can do after

Understand how a query helps determine attention weights over values in a sequence.

How it connects

Connects queries to keys, values, self-attention, softmax, and Transformer models.

liveBookmanning.com

Read Learn Generative AI with PyTorch on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Transformers in ActionIn attention, a query is a vector representation that specifies the information for which relevance is being evaluated.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)A query is an attention vector representing the information whose relevance to sequence elements is being evaluated.
• 

  liveBookmanning.com
  Sutskever's ListAn attention projection representing the information a sequence position seeks from other positions.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA learned projection of an input position used to score how relevant other positions are in attention.
• 

  liveBookmanning.com
  Deep Learning with Python, Third Edition
• 

  liveBookmanning.com
  How Large Language Models WorkAn attention query is a vector representing the information sought when an attention operation compares sequence elements.

Compare how 7 books explain query →

Related concepts

• attentionused by · Attention is a neural-network mechanism that computes input-dependent weights to combine information according to its relevance to a computation.
• inner productuses · An inner product is a scalar-valued operation on two vectors that combines their corresponding components, summing their products and, for complex vectors, using conjugation.
• scaled-dot product attentionused by · Scaled dot-product attention computes query-key dot products, divides them by the square root of the key dimension, applies softmax, and uses the resulting weights to combine value vectors.
• Rotary Position Embeddingused by · Rotary Position Embedding is a positional encoding method that represents token positions by applying position-dependent rotations to components of attention query and key vectors.
• keyuses · In attention, a key is a vector representation of an input element that is compared with a query to determine relevance and attention weights for its associated value.

This explainer was generated by Manning's knowledge graph from the text of Learn Generative AI with PyTorch. The section links point to the parts of the book it draws on.