shadow-peft-models
Collection
pretrained weights and data for the ShadowPEFT paper • 30 items • Updated • 4
How to use shadow-llm/Qwen3-4B-MMLU-LoRA with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("shadow-llm/Qwen3-4B-MMLU-LoRA", dtype="auto")@article{li2026shadowpeft,
title={ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning},
author={Xianming Li and Zongxi Li and Tsz-fung Andrew Lee and Jing Li and Haoran Xie and Qing Li},
year={2026},
eprint={2604.19254},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2604.19254},
}