Sequence architectures and attention · MLD-1060
Rotary position embedding
Encoding position by rotating query and key vector components so dot products depend on relative offsets.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Supply positional information in attention.
Original caveat
Long-context behavior depends on frequency and scaling choices.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · NLP.
Aliases: RoPE.
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 ↗