Public preview: catalog and authors' cards only, no downloads. Hospital agents use the intranet instance.

Models 15

Sort: NameMost downloadsMost likesSize (small → large)Size (large → small)

✕ Clear filters

🧩 timm/vit_huge_patch14_clip_224.laion2b
General·General vision ·2.53 GB ·↓ 899
`timm` CLIP (image encoder only) weights from https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K
🧩 timm/vit_large_patch14_clip_224.openai
General·General vision ·3.43 GB ·↓ 77,577 ·♥ 2
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
General·General vision ·0.44 GB ·↓ 11,738
A ConvNeXt image classification model. Pretrained on ImageNet-22k by paper authors.
🧩 timm/convnext_large.fb_in22k
General·General vision ·0.92 GB ·↓ 1,465
A ConvNeXt image classification model. Pretrained on ImageNet-22k by paper authors.
🧩 timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k
General·General vision ·3.39 GB ·↓ 1,779 ·♥ 5
A ConvNeXt image classification model. CLIP image tower weights pretrained in OpenCLIP on LAION and fine-tuned on ImageNet-1k in `timm` by R…
🧩 timm/densenet121.tv_in1k
General·General vision ·0.03 GB ·↓ 108,363
A DenseNet image classification model. Trained on ImageNet-1k (original torchvision weights).
🧩 timm/efficientnet_b3.ra2_in1k
General·General vision ·0.05 GB ·↓ 117,864 ·♥ 31
A EfficientNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below.
🧩 timm/efficientnetv2_rw_m.agc_in1k
General·General vision ·0.21 GB ·↓ 150,077 ·♥ 2
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
General·General vision ·0.35 GB ·↓ 91,429 ·♥ 9
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
General·General vision ·1.22 GB ·↓ 26,000 ·♥ 26
An EVA02 image classification model. Pretrained on Merged-38M (IN-22K, CC12M, CC3M, COCO (train), ADE20K (train), Object365, and OpenImages)…
🧩 timm/regnety_160.swag_ft_in1k
General·General vision ·0.33 GB ·↓ 749
A RegNetY-16GF image classification model. Pretrained according to SWAG: weakly-supervised learning on ~3.6B Instagram images and associated…
🧩 timm/resnet152.a1h_in1k
General·General vision ·0.24 GB ·↓ 3,447
Trained on ImageNet-1k in `timm` using recipe template described below.
🧩 timm/resnet50.a1_in1k
General·General vision ·0.1 GB ·↓ 1,472,580 ·♥ 50
Trained on ImageNet-1k in `timm` using recipe template described below.
🧩 timm/swin_large_patch4_window12_384.ms_in22k
General·General vision ·0.93 GB ·↓ 1,847 ·♥ 2
A Swin Transformer image classification model. Pretrained on ImageNet-22k by paper authors.
🧩 timm/vit_base_patch16_224.augreg_in21k
General·General vision ·0.41 GB ·↓ 43,733 ·♥ 11
A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k (with additional augmentation and regularization) in JAX by p…