Open Models Almanac
Methodstraining objectivedistillation objective

specific method · filed under training objective

Temperature-scaled forward-KL distillation

A forward-KL loss with temperature is computed against backbone logits.

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

Also called temperature-scaled forward-KL loss.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Evidence

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

How sources treat it
used 2
↑