socius/Smoltaur-1.7B-LoRA-r16-f0.5

<div align="center"> <img src="Smoltaur-1.7B-LoRA-r16-f0.5.png" alt="Smoltaur-1.7B-LoRA-r16-f0.5" width="1000">


      </div>

Smoltaur-1.7B-LoRA-r16-f0.5

LoRA adapter for Smoltaur-1.7B, fine-tuned on a stratified 50% 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/SmolLM2-1.7B, or evaluate with the project's eval_model.py --backend unsloth.