Sequence architectures and attention · MLD-0604
Key
A vector used to score how relevant a position is to attention queries.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Match a token against other positions.
Original caveat
Keys do not directly contain the weighted output contribution.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · NLP.
Aliases: K (attention).
Related concepts
Concepts linking here
Original references
- Attention Is All You Need ↗ · Consulted
- Transformers glossary ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗