Downloads · 30 days
20
36% of all-time downloads
Llama-Centaur-3B-LoRA-r8
socius/Llama-Centaur-3B-LoRA-r8
Llama-Centaur-3B-LoRA-r8 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 llama3.2.
<div align="center" <img src="Llama-Centaur-3B-LoRA-r8.png" alt="Llama-Centaur-3B-LoRA-r8" width="1000"
All-time downloads
56
Public
Repo size
314 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors243 MB · 56%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- llama3.2
- Access
- Public
- Created
- Jun 8, 2026
- Updated
- Aug 7, 2026
- SHA
- c5dca8fa
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<div align="center">
<img src="Llama-Centaur-3B-LoRA-r8.png" alt="Llama-Centaur-3B-LoRA-r8" width="1000">
Llama-Centaur-3B-LoRA-r8
LoRA adapter for Llama-Centaur-3B, 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/Llama-3.2-3B |
| LoRA rank | 8 (alpha = rank, rsLoRA) |
| data fraction | 100% of Psych-101 |
| training | 1 epoch, completion-only loss, seed 3407 |
Load with PEFT on top of unsloth/Llama-3.2-3B, or evaluate with the project's
eval_model.py --backend unsloth.
- Task
- Text Generation
- Library
- peft
- License
- llama3.2
- Languages
- en
- Created
- Jun 8, 2026
- Updated
- Aug 7, 2026