socius/Qwentaur-0.6B-LoRA-r16-f0.25
<div align="center"> <img src="Qwentaur-0.6B-LoRA-r16-f0.25.png" alt="Qwentaur-0.6B-LoRA-r16-f0.25" width="1000">

      </div>
Qwentaur-0.6B-LoRA-r16-f0.25
LoRA adapter for Qwentaur-0.6B, fine-tuned on a stratified 25% subset of Psych-101 as part of the LoRA-rank sweep and dataset-size ablation for Small Foundation Models of Human Cognition and Behaviour.
Load with PEFT on top of unsloth/Qwen3-0.6B-Base, or evaluate with the project's eval_model.py --backend unsloth.
