ys-zong's picture
Create README.md
54c0efd verified
metadata
language:
  - en

VLGuard

[Website] [Paper] [Code]

Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models. (ICML 2024)

Weights

This is the model weights for LLaVA-v1.5-13B 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.

Usage

Please refer to Github for detailed usage.