Tokenization and text representation · MLD-0134
BOS token
A marker indicating the beginning of a sequence.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Initialize generation with a designated start token.
Original caveat
Not every model requires an explicit BOS token.
Context and aliases
Level: Intermediate. Stages: Data · Training · Inference.
Tags: NLP · SLM · LLM.
Aliases: Beginning-of-sequence 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 ↗