Models 101
facebook/vit-msn-large
Vision Transformer (ViT) model pre-trained using the MSN method. It was introduced in the paper Masked Siamese Networks for Label-Efficient…
facebook/PE-Core-B16-224
[\\[📃 Tech Report\\]](https://arxiv.org/abs/2504.13181) [\\[📂 Github\\]](https://github.com/facebookresearch/perception_models/)
facebook/PE-Core-G14-448
[\[📃 Tech Report\]](https://arxiv.org/abs/2504.13181) [\[📂 Github\]](https://github.com/facebookresearch/perception_models/)
facebook/PE-Core-L14-336
[\[📃 Tech Report\]](https://arxiv.org/abs/2504.13181) [\[📂 Github\]](https://github.com/facebookresearch/perception_models/)
facebook/PE-Spatial-G14-448
[\[📃 Tech Report\]](https://arxiv.org/abs/2504.13181) [\[📂 Github\]](https://github.com/facebookresearch/perception_models/)
ryanyip7777/pmc_vit_l_14
The model is fine-tuned from openai's ViT-L-14 using PMC_OA_beta and roco's data sets, using the tool open_clip（https://github.com/mlfoundat…
flaviagiammarino/pubmed-clip-vit-base-patch32
PubMedCLIP is a fine-tuned version of CLIP for the medical domain.
nvidia/RADIO-L
Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov
timm/regnety_160.swag_ft_in1k
A RegNetY-16GF image classification model. Pretrained according to SWAG: weakly-supervised learning on ~3.6B Instagram images and associated…
timm/resnet152.a1h_in1k
Trained on ImageNet-1k in `timm` using recipe template described below.
timm/resnet50.a1_in1k
Trained on ImageNet-1k in `timm` using recipe template described below.
PekingU/rtdetr_v2_r50vd
The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian…
facebook/sam-vit-base
Detailed architecture of Segment Anything Model (SAM).
facebook/sam-vit-huge
Detailed architecture of Segment Anything Model (SAM).
facebook/sam-vit-large
Detailed architecture of Segment Anything Model (SAM).
facebook/sam2.1-hiera-base-plus
Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and…
facebook/sam2.1-hiera-large
Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and…
facebook/sam2.1-hiera-small
Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and…
facebook/sam2.1-hiera-tiny
Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and…
facebook/sam3
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text o…
nvidia/segformer-b5-finetuned-ade-640-640
SegFormer model fine-tuned on ADE20k at resolution 640x640. It was introduced in the paper SegFormer: Simple and Efficient Design for Semant…
google/siglip-base-patch16-224
SigLIP model pre-trained on WebLi at resolution 224x224. It was introduced in the paper Sigmoid Loss for Language Image Pre-Training by Zhai…
google/siglip-so400m-patch14-384
SigLIP model pre-trained on WebLi at resolution 384x384. It was introduced in the paper Sigmoid Loss for Language Image Pre-Training by Zhai…
google/siglip2-base-patch16-224
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved sema…
google/siglip2-giant-opt-patch16-384
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved sema…
google/siglip2-large-patch16-256
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved sema…
google/siglip2-so400m-patch14-384
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved sema…
google/siglip2-so400m-patch16-512
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved sema…
timm/swin_large_patch4_window12_384.ms_in22k
A Swin Transformer image classification model. Pretrained on ImageNet-22k by paper authors.
microsoft/swinv2-large-patch4-window12-192-22k
Swin Transformer v2 model pre-trained on ImageNet-21k at resolution 192x192. It was introduced in the paper Swin Transformer V2: Scaling Up…