metadata
license: apache-2.0
datasets:
- marcelbinz/Psych-101
language:
- en
base_model:
- unsloth/Qwen3-14B-Base
base_model_relation: adapter
pipeline_tag: text-generation
library_name: peft
tags:
- psychology
- cognitive science
- human behavior
- unsloth
- lora
Qwentaur-14B-LoRA-r16
LoRA adapter for Qwentaur-14B, 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.
| field | value |
|---|---|
| base model | unsloth/Qwen3-14B-Base |
| LoRA rank | 16 (alpha = rank, rsLoRA) |
| data fraction | 100% of Psych-101 |
| training | 1 epoch, completion-only loss, seed 3407 |
Load with PEFT on top of unsloth/Qwen3-14B-Base, or evaluate with the project's
eval_model.py --backend unsloth.