VLGuard

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

Weights

This is the model weights for LLaVA-v1.5-7B Posthoc Fine-tuning with LoRA. You can use them in exactly the same way as the original LLaVA.

Please refer to Github for detailed usage.

Safetensors

Model size

7.06B params

Tensor type

F32

FP16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.