Downloads · 30 days
36
20% of all-time downloads
Qwentaur-8B-LoRA-r16
socius/Qwentaur-8B-LoRA-r16
Qwentaur-8B-LoRA-r16 is a text generation model from socius. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
<div align="center" <img src="Qwentaur-8B-LoRA-r16.png" alt="Qwentaur-8B-LoRA-r16" width="1000"
All-time downloads
184
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors873 MB · 67%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jan 22, 2026
- Updated
- Aug 7, 2026
- SHA
- cc6b9e26
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<div align="center">
<img src="Qwentaur-8B-LoRA-r16.png" alt="Qwentaur-8B-LoRA-r16" width="1000">
Qwentaur-8B-LoRA-r16
LoRA adapter for Qwentaur-8B, 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/Qwen3-8B-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/Qwen3-8B-Base, or evaluate with the project's
eval_model.py --backend unsloth.
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Jan 22, 2026
- Updated
- Aug 7, 2026