Tokenization and text representation · MLD-1243
Tokenizer
The algorithm and configuration mapping input to tokens and identifiers, often with a reverse decoding operation.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Use the tokenizer paired with a checkpoint.
Original caveat
A tokenizer mismatch can corrupt model behavior.
Context and aliases
Level: Foundational. Stages: Data · Training · Inference.
Tags: NLP · SLM · LLM.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Hugging Face: chat templates ↗ · Reference link
- Transformers glossary ↗ · Consulted
- Hugging Face: tokenization algorithms ↗ · Consulted
- Original reference URL ↗