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 ↗ · 2026-11-12T02:17:04.301031227ZazureFoundry/azureml/microsoft-beit-base-patch16-224-pt22k-ft22k@19
BEiT (Bidirectional Encoder representation from Image Transformers) is a vision transformer(ViT) pre-trained with Masked Image Modeling(MIM), which is a self-supervised pre-training inspired by BERT from NLP, followed by Intermediate fine-tuning using ImageNet-22k dataset. It is
azureFoundry/HuggingFace/microsoft-beit-base-patch16-384@1
# BEiT (base-sized model, fine-tuned on ImageNet-1k) BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 384x384. It was i
azureFoundry/HuggingFace/microsoft-beit-large-finetuned-ade-640-640@1
`microsoft/beit-large-finetuned-ade-640-640` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/beit-large-finetuned-ade-640-640) - [`image-segmentation` Task on Hugging Face](https://huggingface.co/tasks/image-segmentation) ### S
azureFoundry/HuggingFace/microsoft-beit-large-patch16-224@1
# BEiT (large-sized model, fine-tuned on ImageNet-1k) BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 224x224. It was
azureFoundry/HuggingFace/microsoft-beit-large-patch16-224-pt22k-ft22k@1
# BEiT (large-sized model, fine-tuned on ImageNet-22k) BEiT model pre-trained in a self-supervised fashion on ImageNet-22k - also called ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on the same dataset at resolution 224x224. It was int
azureFoundry/HuggingFace/microsoft-beit-large-patch16-384@1
# BEiT (large-sized model, fine-tuned on ImageNet-1k) BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 384x384. It was
azureFoundry/HuggingFace/microsoft-beit-large-patch16-512@1
# BEiT (large-sized model, fine-tuned on ImageNet-1k) BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 512x512. It was
azureFoundry/HuggingFace/microsoft-biogpt@7
`microsoft/biogpt` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases, you c
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-biogpt-large@5
## BioGPT Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Among the two main branches of pre-trained language models in the general language domain, i.e. BERT (and
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-biogpt-large-pubmedqa@3
## BioGPT Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Among the two main branches of pre-trained language models in the general language domain, i.e. BERT (and
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-biomednlp-biomedbert-base-uncased-abstract@1
## MSR BiomedBERT (abstracts only) <div style="border: 2px solid orange; border-radius:10px; padding:0px 10px; width: fit-content;"> * This model was previously named **"PubMedBERT (abstracts)"**. * You can either adopt the new model name "microsoft/BiomedNLP-BiomedBERT-base-u
huggingface/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
azureFoundry/HuggingFace/microsoft-biomednlp-biomedbert-large-uncased-abstract@1
## MSR BiomedBERT-large (abstracts only) <div style="border: 2px solid orange; border-radius:10px; padding:0px 10px; width: fit-content;"> * This model was previously named **"PubMedBERT large (abstracts)"**. * You can either adopt the new model name "microsoft/BiomedNLP-Biome
azureFoundry/HuggingFace/microsoft-biomednlp-krissbert-pubmed-umls-el@1
## KRISSBERT [https://arxiv.org/pdf/2112.07887.pdf](https://arxiv.org/pdf/2112.07887.pdf) Entity linking faces significant challenges such as prolific variations and prevalent ambiguities, especially in high-value domains with myriad entities. Standard classification approache
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
azureFoundry/HuggingFace/microsoft-biomednlp-pubmedbert-base-uncased-abstract@8
`microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `fill-mask` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters,
azureFoundry/HuggingFace/microsoft-biomednlp-pubmedbert-base-uncased-abstract-fulltext@11
`microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `fill-mask` task in the `transformers` library. If you want to learn more about the model's architecture, hyperpar
azureFoundry/HuggingFace/microsoft-biomednlp-pubmedbert-large-uncased-abstract@4
## MSR BiomedBERT-large (abstracts only) <div style="border: 2px solid orange; border-radius:10px; padding:0px 10px; width: fit-content;"> * This model was previously named **"PubMedBERT large (abstracts)"**. * You can either adopt the new model name "microsoft/BiomedNLP-Biome
azureFoundry/HuggingFace/microsoft-biomedvlp-cxr-bert-general@11
# CXR-BERT-general [CXR-BERT](https://arxiv.org/abs/2204.09817) is a chest X-ray (CXR) domain-specific language model that makes use of an improved vocabulary, novel pretraining procedure, weight regularization, and text augmentations. The resulting model demonstrates improved