← All parts of this equation

Equation 4 · Part 7 · How Llama's Architecture Actually Works, Generation by Generation

superscript

θi=base−2(i−1)/d,i=1,…,d/2,\theta_i = \text{base}^{-2(i-1)/d}, \qquad i = 1, \dots, d/2,
superscript

What this part means

A raised number can be a power. When it is a label or bound, it selects a case or the upper limit of a sum; the formula’s structure distinguishes these uses.

Its job in the formula

A raised mark can be a power or an index. Its position and the surrounding notation determine which.

The passage around this formula

Split each query or key vector of dimension d into d/2 two-dimensional pairs. Pair i is assigned a fixed rotation frequency θi=base−2(i−1)/d,i=1,…,d/2\theta_i = \text{base}^{-2(i-1)/d}, \qquad i = 1, \dots, d/2. and a vector at sequence position m has its i -th pair rotated by angle mθi\theta_i :

Read this part in the article →

Learn the underlying idea

An exponent tells how a base is used in multiplication. In x³, x is the base and 3 is the exponent: x³ = x × x × x.

Open the illustrated exponents: repeated multiplication and powers guide →

Sources cited in the article section

These citations provide research context; check each source for the exact claim it supports.