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/HuggingFace/microsoft-bitnet-b1-58-2b-4t@3
`microsoft/bitnet-b1.58-2B-4T` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T) ### Send Request You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token. ```bas
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-chatbench-distilgpt2@1
`microsoft/chatbench-distilgpt2` powered by Hugging Face API - [Original Model Card](https://huggingface.co/microsoft/chatbench-distilgpt2) - [`text-generation` Task on Hugging Face](https://huggingface.co/tasks/text-generation) ### Send Request You can use cURL or any REST Cl
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-codebert-base@1
## CodeBERT-base Pretrained weights for [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://arxiv.org/abs/2002.08155). ### Training Data The model is trained on bi-modal data (documents & code) of [CodeSearchNet](https://github.com/github/CodeSearchNet)
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
azureFoundry/HuggingFace/microsoft-codebert-base-mlm@6
`microsoft/codebert-base-mlm` 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, limitations, and biases,
azureFoundry/HuggingFace/microsoft-codegpt-small-java@3
`microsoft/CodeGPT-small-java` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/microsoft/CodeGPT-small-java) - [Text Generation Inference Documen
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-microsoft/models/codegpt-small-java-adaptedgpt2@001
azureFoundry/HuggingFace/microsoft-codegpt-small-py@3
`microsoft/CodeGPT-small-py` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/microsoft/CodeGPT-small-py) - [Text Generation Inference Documentati
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 29.167%
vertexAI/publishers/hf-microsoft/models/codereviewer@001
azureFoundry/HuggingFace/microsoft-conditional-detr-resnet-50@1
# Conditional DETR model with ResNet-50 backbone Conditional DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images). It was introduced in the paper [Conditional DETR for Fast Training Convergence](https://arxiv.org/abs/2108.0
azureFoundry/HuggingFace/microsoft-cvt-13@1
`microsoft/cvt-13` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/cvt-13) - [`image-classification` Task on Hugging Face](https://huggingface.co/tasks/image-classification) ### Send Request You can use cURL or any REST Client
azureFoundry/HuggingFace/microsoft-cvt-13-384@1
# Convolutional Vision Transformer (CvT) CvT-13 model pre-trained on ImageNet-1k at resolution 384x384. It was introduced in the paper [CvT: Introducing Convolutions to Vision Transformers](https://arxiv.org/abs/2103.15808) by Wu et al. and first released in [this repository](h
azureFoundry/HuggingFace/microsoft-cvt-13-384-22k@1
# Convolutional Vision Transformer (CvT) CvT-13 model pre-trained on ImageNet-22k and fine-tuned on ImageNet-1k at resolution 384x384. It was introduced in the paper [CvT: Introducing Convolutions to Vision Transformers](https://arxiv.org/abs/2103.15808) by Wu et al. and first
azureFoundry/HuggingFace/microsoft-cvt-21@1
# Convolutional Vision Transformer (CvT) CvT-21 model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [CvT: Introducing Convolutions to Vision Transformers](https://arxiv.org/abs/2103.15808) by Wu et al. and first released in [this repository](h
azureFoundry/HuggingFace/microsoft-cvt-21-384@1
# Convolutional Vision Transformer (CvT) CvT-21 model pre-trained on ImageNet-1k at resolution 384x384. It was introduced in the paper [CvT: Introducing Convolutions to Vision Transformers](https://arxiv.org/abs/2103.15808) by Wu et al. and first released in [this repository](h
azureFoundry/HuggingFace/microsoft-cvt-21-384-22k@1
# Convolutional Vision Transformer (CvT) CvT-21 model pre-trained on ImageNet-22k and fine-tuned on ImageNet-1k at resolution 384x384. It was introduced in the paper [CvT: Introducing Convolutions to Vision Transformers](https://arxiv.org/abs/2103.15808) by Wu et al. and first
azureFoundry/HuggingFace/microsoft-cvt-w24-384-22k@1
# Convolutional Vision Transformer (CvT) CvT-w24 model pre-trained on ImageNet-22k and fine-tuned on ImageNet-1k at resolution 384x384. It was introduced in the paper [CvT: Introducing Convolutions to Vision Transformers](https://arxiv.org/abs/2103.15808) by Wu et al. and first
azureFoundry/HuggingFace/microsoft-dayhoff-170m-gr@4
# Model Card for microsoft/Dayhoff-170m-GR Dayhoff is an Atlas of both protein sequence data and generative language models — a centralized resource that brings together 3.34 billion protein sequences across 1.7 billion clusters of metagenomic and natural protein sequences (Gig
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-dayhoff-170m-ur50@1
`microsoft/Dayhoff-170m-UR50` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/Dayhoff-170m-UR50) ### Send Request You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token. ```bash
- Input modalities
- text
- Output modalities
- text