Open Models Almanac
Methodsmodel architecturepositional encoding

implementation detail · filed under model architecture

YaRN scaling-factor selection

This implementation detail selects or adjusts YaRN's scaling factor based on target or typical context length and workload.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See positional encoding for the methods filed beside it.

Also called modify the factor as needed, Pick factor to match your real workload.

sources
2
models
2
lab adopt it
1
strongest
optional

Documented in

Evidence

3 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
optional 3

Qwen3.5-397B-A17B

Alibaba (Qwen)adopted1 source

It is also recommended to modify the factor as needed. For example, if the typical context length for your application is 524,288 tokens, it would be better to set factor as 2.0.

optionalinference servingin Qwen3.5-35B-A3BQwen Team
1 more from this model

if the typical context length for your application is 524,288 tokens

optionalinference servingin Qwen3.5-35B-A3BQwen Team
↑