Open Models Almanac
Methodsdata curationdata mixture & curriculum

single mention · data curation

Mix supervised fine-tuning data with teacher-generated reinforcement-learning rollouts

Blending supervised fine-tuning examples with teacher-generated RL rollouts at a specified mixture proportion.

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

Filed under data curation › data mixture & curriculum