π₯οΈ GPUFP16~17 GB7B params
β¬ 106β₯ 11visual-question-answering
Multimodalapache-2.0
dataset:lmms-lab/llava-onevision-datadataset:allenai/pixmo-docsdataset:huggingfacem4/docmatixdataset:lmms-lab/llava-video-178k
View on Hugging Faceπ₯οΈ GPUFP16~22 GB9B params
β¬ 105β₯ 0visual-question-answering
Multimodalmit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~5 GB2B params
β¬ 105β₯ 6visual-question-answering
Multimodalapache-2.0
chatlicense:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 104β₯ 7video-classification
Videomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~20 GB8B params
β¬ 104β₯ 0visual-question-answering
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 104β₯ 0visual-question-answering
Multimodalapache-2.0
dataset:lmms-lab/vqav2license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 101β₯ 5video-classification
Videomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~8 GB3B params
β¬ 101β₯ 3visual-question-answering
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16~17 GB7B params
β¬ 101β₯ 28visual-question-answering
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 100β₯ 1video-classification
Videomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 99β₯ 5video-classification
Videomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~168 GB70B params
β¬ 99β₯ 10visual-question-answering
Multimodalapache-2.0
dataset:liuhaotian/llava-instruct-150klicense:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16~77 GB32B params
β¬ 99β₯ 3video-classification
Videoapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 98β₯ 4video-classification
Videomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~5 GB2B params
β¬ 98β₯ 5visual-question-answering
Multimodalmit
dataset:tiger-lab/mantis-instructlicense:mit
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 98β₯ 18visual-question-answering
Multimodalapache-2.0
dataset:sbu_captionsdataset:visual_genomedataset:huggingfacem4/vqav2license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 97β₯ 3video-classification
Videomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~17 GB7B params
β¬ 96β₯ 12visual-question-answering
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 95β₯ 0video-classification
Videomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 95β₯ 8video-classification
Videomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~564 GB235B params
β¬ 95β₯ 1visual-question-answering
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16~20 GB8B paramsπ Gated
β¬ 95β₯ 21visual-question-answering
Multimodalapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUGPTQ
β¬ 92β₯ 0visual-question-answering
Multimodalmit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~5 GB2B params
β¬ 92β₯ 0visual-question-answering
Multimodalapache-2.0
license:apache-2.0
View on Hugging Face