Hugging Face's logo

socius
/
Smoltaur-0.4B-LoRA-r16

Text Generation
PEFT
Safetensors
English
psychology
cognitive science
human behavior
unsloth
lora
Model card Files
xet
 Community
Smoltaur-0.4B-LoRA-r16

Hugging Face

socius Paper Parameters LoRA Dataset

Smoltaur-0.4B-LoRA-r16

LoRA adapter for Smoltaur-0.4B, 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/SmolLM2-360M
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/SmolLM2-360M, or evaluate with the project's eval_model.py --backend unsloth.

Downloads last month
8
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for socius/Smoltaur-0.4B-LoRA-r16

Base model

HuggingFaceTB/SmolLM2-360M
Finetuned
unsloth/SmolLM2-360M
Adapter
(208)
this model

Dataset used to train socius/Smoltaur-0.4B-LoRA-r16

Collection including socius/Smoltaur-0.4B-LoRA-r16

Paper for socius/Smoltaur-0.4B-LoRA-r16