Sequence architectures and attention · MLD-1015
Relative position encoding
A representation or bias based on pairwise position differences.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Model token relationships by relative distance.
Original caveat
Implementations use different parameterizations.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · NLP.
Aliases: None recorded.
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 ↗