Tokenization and text representation · MLD-1288
Unknown token
A special token used for input units the tokenizer cannot represent directly.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Handle an unsupported word in a fixed-word vocabulary.
Original caveat
Some byte-based tokenizers rarely need this mechanism.
Context and aliases
Level: Intermediate. Stages: Data · Training · Inference.
Tags: NLP · SLM · LLM.
Aliases: UNK token.
Related concepts
Concepts linking here
Original references
- Hugging Face: chat templates ↗ · Reference link
- Transformers glossary ↗ · Consulted
- Hugging Face: tokenization algorithms ↗ · Consulted
- Original reference URL ↗