{
"_id": "621ffdc136468d709f17a32e",
"id": "dandelin/vilt-b32-finetuned-vqa",
"private": false,
"pipeline_tag": "visual-question-answering",
"library_name": "transformers",
"tags": [
"transformers",
"pytorch",
"vilt",
"visual-question-answering",
"arxiv:2102.03334",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"downloads": 69681,
"likes": 416,
"modelId": "dandelin/vilt-b32-finetuned-vqa",
"author": "dandelin",
"sha": "d0a1f6ab88522427a7ae76ceb6e1e1e7b68a1d08",
"lastModified": "2022-08-02T13:03:04.000Z",
"gated": false,
"disabled": false,
"widgetData": [
{
"text": "What's the animal doing?",
"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg"
},
{
"text": "What is on top of the building?",
"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg"
}
],
"model-index": null,
"config": {
"architectures": [
"ViltForVisualQuestionAnswering"
],
"model_type": "vilt",
"tokenizer_config": {
"unk_token": "[UNK]",
"sep_token": "[SEP]",
"pad_token": "[PAD]",
"cls_token": "[CLS]",
"mask_token": "[MASK]"
}
},
"cardData": {
"tags": [
"visual-question-answering"
],
"license": "apache-2.0",
"widget": [
{
"text": "What's the animal doing?",
"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg"
},
{
"text": "What is on top of the building?",
"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg"
}
]
},
"transformersInfo": {
"auto_model": "ViltForVisualQuestionAnswering",
"processor": "AutoProcessor"
},
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "config.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "pytorch_model.bin"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.txt"
}
],
"spaces": [
"microsoft/HuggingGPT",
"gunship999/SexyImages",
"Yntec/ToyWorld",
"llamameta/flux-pro-uncensored",
"Uthar/SexyReality",
"Yntec/PrintingPress",
"Nymbo/Compare-6",
"nielsr/comparing-VQA-models",
"llamameta/fluxproV2",
"phenixrhyder/NSFW-ToyWorld",
"Yntec/ToyWorldXL",
"Yntec/blitz_diffusion",
"nielsr/vilt-vqa",
"John6666/Diffusion80XX4sg",
"ethanchern/Anole",
"John6666/PrintingPress4",
"llamameta/fast-sd3.5-large",
"martynka/TasiaExperiment",
"yergyerg/ImgGenClone",
"Yntec/Image-Models-Test-2024",
"Yntec/Image-Models-Test-April-2024",
"DemiPoto/TestDifs",
"Abinivesh/Multi-models-prompt-to-image-generation",
"NativeAngels/Compare-6",
"John6666/hfd_test_nostopbutton",
"taesiri/HuggingGPT-Lite",
"Nymbo/Diffusion80XX4sg",
"DemiPoto/testSortModels",
"kaleidoskop-hug/PrintingPress",
"Yntec/MiniToyWorld",
"ixxan/cross-lingual-vqa",
"John6666/ToyWorld4",
"Madhuri/vqa_audiobot",
"John6666/Diffusion80XX4g",
"SAITAN666/StableDiffusion35Large-Image-Models-Test-November-2024",
"NativeAngels/HuggingfaceDiffusion",
"Yntec/Image-Models-Test-December-2024",
"huggingfacejs/doc-vis-qa",
"John6666/Diffusion80XX4",
"K00B404/HuggingfaceDiffusion_custom",
"John6666/blitz_diffusion4",
"John6666/blitz_diffusion_builtin",
"K00B404/SimpleBrothel",
"optowo/dandelin-vilt-b32-finetuned-vqa",
"Babyloncoder/chat-with-an-image",
"Blane187/multi-diffusion",
"OpenXAIProject/pnpxai-image-classification",
"NativeAngels/ToyWorld",
"Uthar/LewdExperiments",
"Uthar/BodyPaint",
"Uthar/HRGiger",
"Uthar/HighFashion",
"BarBar288/Chatbot",
"hayas-tohoku-workshop-2023/comparing-VQA-models",
"dreamdrop-art/000555111",
"SeyedAli/Persian-Visual-Question-Answering-1",
"sathvikparasa20/vqa-vitgpt",
"romadanskiy/open-source-models-hg",
"Yeeezus/SexyImages",
"John6666/MiniToyWorld",
"luck210/gemma",
"Ane4ka/422_MTDDP",
"ccarr0807/HuggingGPT",
"theholycityweb/HuggingGPT",
"gtx4010661/dandelin-vilt-b32-finetuned-vqa",
"Alfasign/HuggingGPT-Lite",
"roontoon/Demo-TTI-dandelin-vilt-b32-finetuned-vqa",
"nilaymodi/dandelin-vilt-b32-finetuned-vqa",
"saurshaz/HuggingGPT",
"Akoloskov/image-recon",
"Nikhil0987/omm",
"wendys-llc/comparing-VQA-models",
"SilvusTV/Test",
"roshithindia/imageQuestionAnswering",
"mahitha11/vqa-vitgpt",
"TotoB12/dandelin-vilt-b32-finetuned-vqa",
"Geek7/mdztxi2",
"NativeAngels/blitz_diffusion",
"NativeAngels/PrintingPress4",
"NativeAngels/PrintingPress",
"dehua68/ToyWorld",
"Uthar/Harvester",
"JarvisOnSolana/Jarvis",
"codelion/sentinel",
"MrRokot/GENFLUX",
"Hadiil/home23",
"BarBar288/AI_Tools",
"burman-ai/Printing-Press",
"ikraamkb/qtAnswering",
"charliebaby2023/infnapitoggle",
"slayton22slayton/infnapitoggle",
"Uthar/TestgroundPub",
"itsmemauli/product-finder-vqa",
"CJSkeleton/End-to-End_AI_Solution",
"calligraphylab/test",
"rendraep/WebUI_VLM",
"chrisW6825/HuggingGPT",
"Shenziqian/HuggingGPT",
"hema1/Text-Visual-QA",
"lokutus/HuggingGPT"
],
"createdAt": "2022-03-02T23:29:05.000Z",
"usedStorage": 940815323
}