Instructions to use socius/Qwentaur-14B-LoRA-r16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use socius/Qwentaur-14B-LoRA-r16 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-14B-Base") model = PeftModel.from_pretrained(base_model, "socius/Qwentaur-14B-LoRA-r16") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
|
Download README.md from socius/Qwentaur-14B-LoRA-r16: direct link, hf CLI and curl.
- Browser
- Download file 5.61 kB
-
https://huggingface.co/socius/Qwentaur-14B-LoRA-r16/resolve/main/README.md
- Command line
-
hf download hf://socius/Qwentaur-14B-LoRA-r16/README.md
-
curl -L -o README.md https://huggingface.co/socius/Qwentaur-14B-LoRA-r16/resolve/main/README.md
5.61 kB
| license: apache-2.0 | |
| datasets: | |
| - marcelbinz/Psych-101 | |
| language: | |
| - en | |
| base_model: | |
| - unsloth/Qwen3-14B-Base | |
| base_model_relation: adapter | |
| pipeline_tag: text-generation | |
| library_name: peft | |
| tags: | |
| - psychology | |
| - cognitive science | |
| - human behavior | |
| - unsloth | |
| - lora | |
| <div align="center"> | |
| <img src="Qwentaur-14B-LoRA-r16.png" alt="Qwentaur-14B-LoRA-r16" width="1000"> | |
| [](https://huggingface.co/Qwen/Qwen3-14B-Base) | |
| [](https://huggingface.co/collections/socius/qwentaur-14b-lora-6a377e555427d61a91f329d2) | |
| [](https://arxiv.org/abs/2608.05224) | |
| [](https://huggingface.co/socius/Qwentaur-14B-LoRA-r16) | |
| [](https://huggingface.co/socius/Qwentaur-14B-LoRA-r16) | |
| [](https://huggingface.co/datasets/marcelbinz/Psych-101) | |
| </div> | |
| # Qwentaur-14B-LoRA-r16 | |
| LoRA adapter for **Qwentaur-14B**, fine-tuned on the full | |
| [Psych-101](https://huggingface.co/datasets/marcelbinz/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/Qwen3-14B-Base](https://huggingface.co/unsloth/Qwen3-14B-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/Qwen3-14B-Base`, or evaluate with the project's | |
| `eval_model.py --backend unsloth`. | |