yunqing-me

It is usually due to the package version or your installation environment (e.g. cuda). see if this can help: https://github.com/ggerganov/llama.cpp/issues/4702

Thanks for the interest. - For llava, please refer to the official installation: https://github.com/haotian-liu/LLaVA?tab=readme-ov-file#install - For img2prompt, please refer to the base (standard) type implementation of their code: https://github.com/salesforce/LAVIS/blob/main/lavis/models/img2prompt_models/img2prompt_vqa.py

Thanks for the interest. Please adapt our code of crafting adversarial samples shown in the main page to the training / inference code of a specific model as the principal...