Tokenization and text representation · MLD-0306

Detokenization

Converting tokens or token IDs back into text or another output representation.

Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.

Original example

Render generated token IDs as text.

Original caveat

The process may not exactly reverse lossy preprocessing.

Context and aliases

Level: Intermediate. Stages: Data · Training · Inference.

Tags: NLP · SLM · LLM.

Aliases: Token decoding.

Related concepts

Original references

Open original record, export or annotate →