Microsoft

About Microsoft

Explore research at Microsoft, a site featuring the impact of research along with publications, products, downloads, and research careers.

Microsoft Research conducts fundamental science and technology research across a spectrum of research areas. With labs around the globe we pursue breakthroughs across the computing and AI stack to accelerate discovery across sciences and advance the frontiers of computing and AI to create new foundations for others to build upon.

Artificial intelligence | Search & information retrieval | Human language technologies | Human-computer interaction | Computer vision | Graphics & multimedia | Audio & acoustics

Medical, health & genomics | Economics | Social sciences | Technology for emerging markets | Ecology & environment

Website ↗Documentation ↗

Source ↗ · 2026-11-12T02:17:04.301031227Z

669 indexed models

669 matching models

microsoft/SportsBERT

azureFoundry/HuggingFace/microsoft-sportsbert@5

Pretraining large natural language processing models such as BERT, RoBERTa, etc are now state of the art models in natural language understanding and processing tasks. However, these models are trained on a general corpus of articles from the web or from repositories like quora,

microsoft/swin-base-patch4-window12-384

azureFoundry/HuggingFace/microsoft-swin-base-patch4-window12-384@1

# Swin Transformer (base-sized model) Swin Transformer model trained on ImageNet-1k at resolution 384x384. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030) by Liu et al. and first release

microsoft/swin-base-patch4-window12-384-in22k

azureFoundry/HuggingFace/microsoft-swin-base-patch4-window12-384-in22k@1

# Swin Transformer (large-sized model) Swin Transformer model pre-trained on ImageNet-21k (14 million images, 21,841 classes) at resolution 384x384. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2

microsoft/swin-base-patch4-window7-224

azureFoundry/HuggingFace/microsoft-swin-base-patch4-window7-224@2

# Swin Transformer (base-sized model) Swin Transformer model trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030) by Liu et al. and first release

microsoft/swin-large-patch4-window12-384

azureFoundry/HuggingFace/microsoft-swin-large-patch4-window12-384@1

# Swin Transformer (large-sized model) Swin Transformer model trained on ImageNet-1k at resolution 384x384. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030) by Liu et al. and first releas

microsoft/swin-large-patch4-window12-384-in22k

azureFoundry/HuggingFace/microsoft-swin-large-patch4-window12-384-in22k@1

# Swin Transformer (large-sized model) Swin Transformer model pre-trained on ImageNet-21k (14 million images, 21,841 classes) at resolution 384x384. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2

microsoft/swin-large-patch4-window7-224

azureFoundry/HuggingFace/microsoft-swin-large-patch4-window7-224@1

# Swin Transformer (large-sized model) Swin Transformer model trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030) by Liu et al. and first releas

microsoft/swin-large-patch4-window7-224-in22k

azureFoundry/HuggingFace/microsoft-swin-large-patch4-window7-224-in22k@1

# Swin Transformer (large-sized model) Swin Transformer model pre-trained on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2

microsoft/swin-small-patch4-window7-224

azureFoundry/HuggingFace/microsoft-swin-small-patch4-window7-224@1

# Swin Transformer (small-sized model) Swin Transformer model trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030) by Liu et al. and first releas

microsoft/swin-tiny-patch4-window7-224

azureFoundry/HuggingFace/microsoft-swin-tiny-patch4-window7-224@2

# Swin Transformer (tiny-sized model) Swin Transformer model trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030) by Liu et al. and first release

microsoft/swinv2-base-patch4-window12-192-22k

azureFoundry/HuggingFace/microsoft-swinv2-base-patch4-window12-192-22k@1

# Swin Transformer v2 (tiny-sized model) Swin Transformer v2 model pre-trained on ImageNet-21k at resolution 192x192. It was introduced in the paper [Swin Transformer V2: Scaling Up Capacity and Resolution](https://arxiv.org/abs/2111.09883) by Liu et al. and first released in

microsoft-swinv2-base-patch4-window12-192-22k · azureml v15

azureFoundry/azureml/microsoft-swinv2-base-patch4-window12-192-22k@15

The Swin Transformer V2 model is a type of Vision Transformer, pre-trained on ImageNet-21k with a resolution of 192x192, is introduced in the <a href="https://arxiv.org/abs/2111.09883" target="_blank">research-paper</a> titled "Swin Transformer V2: Scaling Up Capacity and Resolut

microsoft-swinv2-base-patch4-window12-192-22k · azureml v17

azureFoundry/azureml/microsoft-swinv2-base-patch4-window12-192-22k@17

The Swin Transformer V2 model is a type of Vision Transformer, pre-trained on ImageNet-21k with a resolution of 192x192, is introduced in the <a href="https://arxiv.org/abs/2111.09883" target="_blank">research-paper</a> titled "Swin Transformer V2: Scaling Up Capacity and Resolut

microsoft-swinv2-base-patch4-window12-192-22k · azureml v19

azureFoundry/azureml/microsoft-swinv2-base-patch4-window12-192-22k@19

The Swin Transformer V2 model is a type of Vision Transformer, pre-trained on ImageNet-21k with a resolution of 192x192, is introduced in the <a href="https://arxiv.org/abs/2111.09883" target="_blank">research-paper</a> titled "Swin Transformer V2: Scaling Up Capacity and Resolut

microsoft-swinv2-base-patch4-window12-192-22k · azureml v20

azureFoundry/azureml/microsoft-swinv2-base-patch4-window12-192-22k@20

The Swin Transformer V2 model is a type of Vision Transformer, pre-trained on ImageNet-21k with a resolution of 192x192, is introduced in the <a href="https://arxiv.org/abs/2111.09883" target="_blank">research-paper</a> titled "Swin Transformer V2: Scaling Up Capacity and Resolut

microsoft-swinv2-base-patch4-window12-192-22k · azureml v21

azureFoundry/azureml/microsoft-swinv2-base-patch4-window12-192-22k@21

The Swin Transformer V2 model is a type of Vision Transformer, pre-trained on ImageNet-21k with a resolution of 192x192, is introduced in the <a href="https://arxiv.org/abs/2111.09883" target="_blank">research-paper</a> titled "Swin Transformer V2: Scaling Up Capacity and Resolut

microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft

azureFoundry/HuggingFace/microsoft-swinv2-base-patch4-window12to16-192to256-22kto1k-ft@1

# Swin Transformer v2 (base-sized model) Swin Transformer v2 model pre-trained on ImageNet-21k and fine-tuned on ImageNet-1k at resolution 256x256. It was introduced in the paper [Swin Transformer V2: Scaling Up Capacity and Resolution](https://arxiv.org/abs/2111.09883) by Liu

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace