Tokenization and text representation · MLD-1287
Unigram tokenizer
A probabilistic subword tokenizer choosing segmentations under a learned unigram vocabulary model.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Find a likely token decomposition of text.
Original caveat
Unigram here describes the segmentation model, not a complete language model.
Context and aliases
Level: Intermediate. 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 ↗