High Tokens Question 148 of 223

What goes wrong if the embedding tokenizer differs from the generator tokenizer?

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

Retrieval still works because embedders have their own tokenizer, but chunk token budgets for the prompt must use the generator's tokenizer.

1

WHY — Tokens instead of words?

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

Tokens 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
    Retrieval still works because

    embedders have their own tokenizer, but chunk token budgets for the prompt must use the generator's tokenizer.

  2. 2
    A chunk that 'fits'

    under the embedder can overflow the LLM context.

  3. 3
    Count prompt tokens with

    the chat model's tokenizer after assembly.

  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

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text
“A chunk that 'fits' under the embedder can overflow the LLM context.”
Tokenized output
Achunkthat'fits'underthe
Token IDs (example)
2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

Key takeaway

Retrieval still works because embedders have their own tokenizer, but chunk token budgets for the prompt must use the generator's tokenizer. A chunk that 'fits' under the embedder can overflow the LLM context.

Chat with us