Sequence architectures and attention · MLD-0868
Padding mask
A mask preventing padded positions from affecting relevant computation.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Batch text sequences of different lengths.
Original caveat
Attention masking and loss masking are separate operations.
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 ↗