Models 101
apple/aimv2-1B-patch14-224
We introduce the AIMv2 family of vision models pre-trained with a multimodal autoregressive objective. AIMv2 pre-training is simple and stra…
apple/aimv2-huge-patch14-448
We introduce the AIMv2 family of vision models pre-trained with a multimodal autoregressive objective. AIMv2 pre-training is simple and stra…
apple/aimv2-large-patch14-224
We introduce the AIMv2 family of vision models pre-trained with a multimodal autoregressive objective. AIMv2 pre-training is simple and stra…
microsoft/beit-large-patch16-224
BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tune…
microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224
BiomedCLIP is a biomedical vision-language foundation model that is pretrained on PMC-15M, a dataset of 15 million figure-caption pairs extr…
microsoft/BiomedParse
This is the official model checkpoint repo for "A foundation model for joint segmentation, detection and recognition of biomedical objects a…
nvidia/C-RADIOv2-B
[**Github**] [**CVPR 2025**] [**CVPR 2024**]
nvidia/C-RADIOv2-H
[**Github**] [**CVPR 2025**] [**CVPR 2024**]
nvidia/C-RADIOv2-L
[**Github**] [**CVPR 2025**] [**CVPR 2024**]
nvidia/C-RADIOv3-H
[**Github**] [**CVPR 2025**] [**CVPR 2024**]
nvidia/C-RADIOv3-L
[**Github**] [**CVPR 2025**] [**CVPR 2024**]
openai/clip-vit-base-patch16
Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found here.
laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
1. Model Details 2. Uses 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation 7. How To Get Started With the Model
timm/vit_huge_patch14_clip_224.laion2b
`timm` CLIP (image encoder only) weights from https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K
laion/CLIP-ViT-H-14-laion2B-s32B-b79K
1. Model Details 2. Uses 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation 7. How To Get Started With the Model
openai/clip-vit-large-patch14
Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found here.
timm/vit_large_patch14_clip_224.openai
The CLIP model was developed by researchers at OpenAI to learn about what contributes to robustness in computer vision tasks. The model was…
timm/convnext_base.fb_in22k
A ConvNeXt image classification model. Pretrained on ImageNet-22k by paper authors.
timm/convnext_large.fb_in22k
A ConvNeXt image classification model. Pretrained on ImageNet-22k by paper authors.
timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k
A ConvNeXt image classification model. CLIP image tower weights pretrained in OpenCLIP on LAION and fine-tuned on ImageNet-1k in `timm` by R…
facebook/convnextv2-huge-22k-512
ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-22K dataset at resolution 512x512. It was introduced i…
facebook/convnextv2-large-22k-224
ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-22K dataset at resolution 224x224. It was introduced i…
timm/densenet121.tv_in1k
A DenseNet image classification model. Trained on ImageNet-1k (original torchvision weights).
depth-anything/Depth-Anything-V2-Base-hf
Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images, providing the most capable monocular depth e…
depth-anything/Depth-Anything-V2-Large-hf
Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images, providing the most capable monocular depth e…
apple/DFN5B-CLIP-ViT-H-14-378
A CLIP (Contrastive Language-Image Pre-training) model trained on DFN-5B. Data Filtering Networks (DFNs) are small networks used to automati…
facebook/dinov2-base
Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features witho…
facebook/dinov2-giant
Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features witho…
facebook/dinov2-large
Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features witho…
facebook/dinov2-with-registers-base
Vision Transformer (ViT) model introduced in the paper Vision Transformers Need Registers by Darcet et al. and first released in this reposi…