Sequence architectures and attention · MLD-0210
Context window
The amount of input and generated sequence context a model or serving configuration can handle in one interaction.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Fit a conversation within a token limit.
Original caveat
Advertised capacity does not guarantee reliable use of every token.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · NLP.
Aliases: Context length limit.
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 ↗