|
--- |
|
language: |
|
- en |
|
--- |
|
# VLGuard |
|
[[Website]](https://ys-zong.github.io/VLGuard) [[Paper]](https://arxiv.org/abs/2402.02207) [[Code]](https://github.com/ys-zong/VLGuard) |
|
|
|
Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models. (ICML 2024) |
|
|
|
|
|
## Weights |
|
This is the model weight for LLaVA-v1.5-7B re-trained with LoRA after removing harmful samples in the training data. You can use them in exactly the same way as the original [LLaVA](https://github.com/haotian-liu/LLaVA/tree/main). |
|
|
|
## Usage |
|
|
|
Please refer to [Github](https://github.com/ys-zong/VLGuard) for detailed usage. |
