Open Models Almanac
Methodspost-trainingsupervised fine-tuning

single mention · post-training

Rank-32 Low-Rank Adaptation

Uses a rank-32 LoRA adapter for robot tool-use fine-tuning.

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.

Also called A rank-32 LoRA adapter.

Filed under post-training › supervised fine-tuning