You can deploy this model and start earning money today!

socius/
Smoltaur-0.4B-LoRA-r32

Name: Smoltaur-0.4B-LoRA-r32
Rating: 2.5 (14 reviews)

Views

No views yet

Hugging Face

socius

Paper

Smoltaur-0.4B-LoRA-r32

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	32 (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.

socius/Smoltaur-0.4B-LoRA-r32

Smoltaur-0.4B-LoRA-r32

socius/
Smoltaur-0.4B-LoRA-r32