CoolFace
Modelpublic

socius/Smoltaur-3B-LoRA-r16-f0.0625

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes9downloads
Model Card

<div align="center"> <img src="Smoltaur-3B-LoRA-r16-f0.0625.png" alt="Smoltaur-3B-LoRA-r16-f0.0625" width="1000">

![Hugging Face](https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base)

![socius](https://huggingface.co/collections/socius/smoltaur-3b-lora-6a6449c3bea837ecbb2c4311) ![Paper](https://arxiv.org/abs/2608.05224) ![Parameters](https://huggingface.co/socius/Smoltaur-3B-LoRA-r16-f0.0625) ![LoRA](https://huggingface.co/socius/Smoltaur-3B-LoRA-r16-f0.0625) ![Dataset](https://huggingface.co/datasets/marcelbinz/Psych-101) ![Data fraction](https://huggingface.co/datasets/marcelbinz/Psych-101) </div>

Smoltaur-3B-LoRA-r16-f0.0625

LoRA adapter for Smoltaur-3B, fine-tuned on a stratified 6.25% subset of Psych-101 as part of the LoRA-rank sweep and dataset-size ablation for Small Foundation Models of Human Cognition and Behaviour.

fieldvalue
base modelunsloth/SmolLM3-3B-Base
LoRA rank16 (alpha = rank, rsLoRA)
data fraction6.25% of Psych-101
training1 epoch, completion-only loss, seed 3407

Load with PEFT on top of unsloth/SmolLM3-3B-Base, or evaluate with the project's eval_model.py --backend unsloth.