Open Models Almanac
Methodspost-training

single mention · post-training

Full post-training using TRL

Describes full post-training conducted using TRL, without specifying its algorithm or stages.

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

Also called full post-training via TRL.

Filed under post-training