Sequence architectures and attention · MLD-0071
Attention mask
A rule or tensor restricting which attention interactions are allowed.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Ignore padding or future token positions.
Original caveat
Mask value conventions differ across APIs.
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 ↗