socius/Qwentaur-1.7B-LoRA-r16
<div align="center"> <img src="Qwentaur-1.7B-LoRA-r16.png" alt="Qwentaur-1.7B-LoRA-r16" width="1000">

     </div>
Qwentaur-1.7B-LoRA-r16
LoRA adapter for Qwentaur-1.7B, fine-tuned on the full 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/Qwen3-1.7B-Base, or evaluate with the project's eval_model.py --backend unsloth.
