payphone131
payphone131
hello, i am trying to reproduce your results in your paper and find there is no autoattack method in your code. i am wondering if you used the code from...
hello, could you provide the images for toxicity detection?
I run the following python code:  but I got:  I also tried this:  but the error kept the same:  My transformers==4.52.0.dev0. I could successfully run the...
1. If I input every frame of this video by multiple-image input, is this somewhat equivalent to video input? 2. How to control the fps of video input?
No matter what the input is, the output is always very short and is bad at answering the question. For example, when the query is 'what is in this image?'...
def test_id_click( accessibility_tree_current_viewport_script_browser_env: ScriptBrowserEnv, ) -> None: env = accessibility_tree_current_viewport_script_browser_env env.reset() obs, success, _, _, info = env.step( create_playwright_action( 'page.goto("https://russmaxdesign.github.io/exercise/")' ) ) assert success assert "link 'McKenna/Bell'" in obs["text"] #...
I tried using liuhaotian/llava-llama-2-13b-chat-lightning-preview on the 40 manual dataset. I found this llava model is very hard to jailbreak even with the adversarial image, which is different from the reported...
hello, could you please provide the adversarial images generated using LLaVA and InstructBLIP?
hello, i find there are two ways of generating texts in your code: in minigpt_test_manual_prompts_visual_llm.py, you use Chat(), ask() and answer() to generate texts; while in minigpt_inference.py, you use Generator(),...