LoRA adapter for Llama-Centaur-8B, 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/Llama-3.1-8B, or evaluate with the project's eval_model.py --backend unsloth.