Open Models Almanac
Methodsmodel architecturetoken mixersparse attentionsparse attention indexer

single mention · model architecture

KL-distillation indexer warm-up

Warms up sparse-attention indexers by distilling the main model's attention distributions with a KL-based objective.

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

Filed under model architecture › token mixer › sparse attention › sparse attention indexer