You can deploy this model and start earning money today!

socius/
Qwentaur-0.6B-LoRA-r16

Name: Qwentaur-0.6B-LoRA-r16
Availability: InStock

unsloth/Qwen3-0.6B-Base

adapter

apache-2.0

Views

No views yet

Qwen

socius

Paper

Qwentaur-0.6B-LoRA-r16

LoRA adapter for Qwentaur-0.6B, 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/Qwen3-0.6B-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/Qwen3-0.6B-Base, or evaluate with the project's eval_model.py --backend unsloth.

socius/Qwentaur-0.6B-LoRA-r16

Qwentaur-0.6B-LoRA-r16

socius/
Qwentaur-0.6B-LoRA-r16