Open Models Almanac
Methodspost-trainingsupervised fine-tuning

single mention · post-training

Fine-tuning on the combined LIBERO training suites

Fine-tunes on the combined Spatial, Object, Goal, and Long suites rather than training a separate model per suite.

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

Filed under post-training › supervised fine-tuning