ModelRefs / ALiBi (Attention with Linear Biases) — AI Glossary
ALiBi (Attention with Linear Biases) — AI Glossary
A positional encoding that adds a linear bias to attention scores based on token distance, enabling context extrapolation.
What this reference supports
ALiBi (Attention with Linear Biases) — AI Glossary: This canonical definition establishes how ModelRefs uses the term and connects it to related implementation concepts. Read the definition in context when a vendor, paper, or benchmark uses a narrower meaning.
ALiBi (Attention with Linear Biases) — AI Glossary: Related references show where the concept appears in models, providers, benchmarks, workflows, architectures, prompts, or tools. Those links distinguish a definition from evidence that a particular system supports it.
ALiBi (Attention with Linear Biases) — AI Glossary: Terminology and implementation practice evolve. Check cited primary material and current documentation when the exact definition, protocol, or product behavior affects a consequential decision.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to ALiBi (Attention with Linear Biases) — AI Glossary.