metadata
license: mit
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- HuggingFaceH4/ultrachat_200k
- walledai/HarmBench
language:
- en
new_version: ASSELab/Diffusion-Llama-3-8B-Instruct
tags:
- pytorch
- llama
- llama-3
- DAT
- robust
- adversarial
library_name: transformers
DAT - Distributional Adversarial Training
DAT utilizes continuous adversarial training on diffusion-based adversarial examples to close the gap between empirical and population-robust risk. We fine-tune meta-llama/Meta-Llama-3-8B-Instruct.
This model is NOT using adversarial training! This is an ablation/baseline using just the diffusion data to fine-tune.
For further information, consult our paper or repository https://github.com/ASSELab/DAT
Citation
@misc{,
title={},
author={},
year={2026},
eprint={},
archivePrefix={arXiv},
primaryClass={cs.LG}
}