Why it matters
ALiBi enables length extrapolation. Understanding shapes long-context.
Advertisement
The architecture
Attention score: Q K^T / sqrt(d) - m_head * (i - j).
m_head: per-head slope.
Advertisement
How it works end to end
Slopes: 2^(-8h/H) for head h of H heads.
No position embedding needed.
Extrapolates beyond training length.