Easy Attention Question 17 of 223

What are queries, keys, and values in attention?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: A SENTENCE BECOMES TOKENS

The model does not read letters like humans. It reads these pieces, then predicts the next one.

Simple meaning

Each token is projected into query, key, and value vectors.

1

WHY — Tokens instead of words?

LLMs use tokens (not full words) because it helps them:

Attention questions separate people

who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

2

STEPS — What happens with tokens?

Before the model can read a sentence, it goes through these steps:

  1. 1
    Each token is projected

    into query, key, and value vectors.

  2. 2
    Compatibility of a query

    with keys decides the attention weights.

  3. 3
    Those weights mix the

    values into the output for that position.

  4. 4
    Context mix

    Attention looks at nearby tokens together.

  5. 5
    Next token

    The model scores what should come next.

  6. 6
    Decode

    IDs turn back into readable text.

3

EXAMPLE — See it in action

Here's a short line you can speak, broken into clear beats:

Say this line
“Compatibility of a query with keys decides the attention weights.”
Break into beats
Compatibilityofaquerywithkeys
Speaking order
2987408337471632900

Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.

Key takeaway

Each token is projected into query, key, and value vectors. Compatibility of a query with keys decides the attention weights.

Previous question Next question
Chat with us