socius/Llama-Centaur-1B-LoRA-r16-f0.125
<div align="center"> <img src="Llama-Centaur-1B-LoRA-r16-f0.125.png" alt="Llama-Centaur-1B-LoRA-r16-f0.125" width="1000">

      </div>
Llama-Centaur-1B-LoRA-r16-f0.125
LoRA adapter for Llama-Centaur-1B, fine-tuned on a stratified 12.5% 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/Llama-3.2-1B, or evaluate with the project's eval_model.py --backend unsloth.
