Open Models Almanac
Methodspost-trainingpolicy distillation

single mention · post-training

IcePop Token-Level Loss Masking

An implementation detail applying token-level loss masking with the IcePop strategy.

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

Also called token-level masking using IcePop strategy.

Filed under post-training › policy distillation