Models 101
facebook/dinov2-with-registers-giant
Vision Transformer (ViT) model introduced in the paper Vision Transformers Need Registers by Darcet et al. and first released in this reposi…
facebook/dinov2-with-registers-large
Vision Transformer (ViT) model introduced in the paper Vision Transformers Need Registers by Darcet et al. and first released in this reposi…
facebook/dinov2-with-registers-small
Vision Transformer (ViT) model introduced in the paper Vision Transformers Need Registers by Darcet et al. and first released in this reposi…
facebook/dinov2-small
Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features witho…
facebook/dinov3-vit7b16-pretrain-lvd1689m
DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings,…
facebook/dinov3-vitb16-pretrain-lvd1689m
DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings,…
facebook/dinov3-convnext-base-pretrain-lvd1689m
DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings,…
facebook/dinov3-convnext-large-pretrain-lvd1689m
DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings,…
facebook/dinov3-vith16plus-pretrain-lvd1689m
DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings,…
facebook/dinov3-vitl16-pretrain-lvd1689m
DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings,…
facebook/dinov3-vits16-pretrain-lvd1689m
DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings,…
timm/efficientnet_b3.ra2_in1k
A EfficientNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below.
timm/efficientnetv2_rw_m.agc_in1k
A EfficientNet-v2 image classification model. This is a `timm` specific variation of the architecture. Trained on ImageNet-1k in `timm` usin…
timm/eva02_base_patch14_448.mim_in22k_ft_in22k_in1k
An EVA02 image classification model. Pretrained on ImageNet-22k with masked image modeling (using EVA-CLIP as a MIM teacher) and fine-tuned…
timm/eva02_large_patch14_448.mim_m38m_ft_in22k_in1k
An EVA02 image classification model. Pretrained on Merged-38M (IN-22K, CC12M, CC3M, COCO (train), ADE20K (train), Object365, and OpenImages)…
IDEA-Research/grounding-dino-base
The Grounding DINO model was proposed in Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection by Shilong L…
facebook/hiera-large-224-hf
Vision transformers like ViT use the same spatial resolution and number of features throughout the whole network. But this is inefficient: t…
facebook/ijepa_vith14_1k
1. without relying on pre-specified invariances to hand-crafted data transformations, which tend to be biased for particular downstream task…
OpenGVLab/InternVideo2-Stage2_1B-224p-f4
This modelcard aims to give the model info of 'InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding'.
OpenGVLab/InternViT-300M-448px-V2_5
[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](…
duynhm/LVM-Med
We release LVM-Med's pre-trained models in PyTorch and demonstrate downstream tasks on 2D-3D segmentations, linear/fully finetuning image cl…
facebook/vit-mae-base
Vision Transformer (ViT) model pre-trained using the MAE method. It was introduced in the paper Masked Autoencoders Are Scalable Vision Lear…
facebook/vit-mae-huge
Vision Transformer (ViT) model pre-trained using the MAE method. It was introduced in the paper Masked Autoencoders Are Scalable Vision Lear…
facebook/vit-mae-large
Vision Transformer (ViT) model pre-trained using the MAE method. It was introduced in the paper Masked Autoencoders Are Scalable Vision Lear…
facebook/mask2former-swin-large-ade-semantic
Mask2Former model trained on ADE20k semantic segmentation (large-sized version, Swin backbone). It was introduced in the paper Masked-attent…
lion-ai/MedImageInsights
This repository provides a simplified implementation for using the MedImageInsight model, an open-source medical imaging embedding model pre…
wanglab/medsam-vit-base
Detailed architecture of Segment Anything Model (SAM).
wanglab/MedSAM2
Jun Ma* 1,2, Zongxin Yang* 3, Sumin Kim2,4,5, Bihui Chen2,4,5, Mohammed Baharoon2,3,5, Adibvafa Fallahpour2,4,5, Reza Asakereh4,7, Hongwei L…
google/medsiglip-448
issues): MedSigLIP GitHub Foundations terms of use](https://developers.google.com/health-ai-developer-foundations/terms).
facebook/metaclip-2-worldwide-huge-quickgelu
MetaCLIP 2 (worldwide) was presented in MetaCLIP 2: A Worldwide Scaling Recipe.