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 ↗ · 2026-11-12T02:17:04.301031227Z669 indexed models
669 matching models
azureFoundry/azureml-msr/microsoft-phi-2@22
## **Microsoft Phi-2** The phi-2 is a language model with 2.7 billion parameters. The phi-2 model was trained using the same data sources as phi-1, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational val
- Input modalities
- text
- Output modalities
- text
huggingface/microsoft/Phi-3.5-vision-instruct
- Capabilities
- multimodal, visionInput
Benchmarks
- LMArena: 919.478
- MMBench: 97.6%
vertexAI/publishers/hf-microsoft/models/phi-3-vision-128k-instruct@001
- Input modalities
- text
- Output modalities
- text
Benchmarks
- LMArena: 881.036
- MMBench: 97.8%
vertexAI/publishers/hf-microsoft/models/phi-4-mini-instruct@001
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 29.412%
vertexAI/publishers/hf-microsoft/models/phi-4-mini-reasoning@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-microsoft/models/phi-mini-moe-instruct@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-microsoft/models/phi-tiny-moe-instruct@001
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-promptist@6
# Promptist: reinforcement learning for automatic prompt optimization ## News - [Demo Release] Dec, 2022: [Demo at HuggingFace Space](https://aka.ms/promptist-demo) - [Model Release] Dec, 2022: [link](#load-pretrained-model-for-stable-diffusion-v14) - [Paper Release] Dec, 2022:
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-prophetnet-large-uncased@5
## prophetnet-large-uncased Pretrained weights for [ProphetNet](https://arxiv.org/abs/2001.04063). ProphetNet is a new pre-trained language model for sequence-to-sequence learning with a novel self-supervised objective called future n-gram prediction. ProphetNet is able to p
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-prophetnet-large-uncased-squad-qg@3
## prophetnet-large-uncased-squad-qg Fine-tuned weights(converted from [original fairseq version repo](https://github.com/microsoft/ProphetNet)) for [ProphetNet](https://arxiv.org/abs/2001.04063) on question generation SQuAD 1.1. ProphetNet is a new pre-trained language mode
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/microsoft-rad-dino@1
## Model Description # Model card for RAD-DINO ## Model description RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt). RAD-DINO is described in detail in [RAD-DI
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
azureFoundry/azureml/microsoft-rad-dino@2
## Model Description # Model card for RAD-DINO ## Model description RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt). RAD-DINO is described in detail in [RAD-DI
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
azureFoundry/azureml/microsoft-rad-dino@3
## Model Description # Model card for RAD-DINO ## Model description RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt). RAD-DINO is described in detail in [RAD-DI
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
azureFoundry/azureml/microsoft-rad-dino@4
## Model Description # Model card for RAD-DINO ## Model description RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt). RAD-DINO is described in detail in [RAD-DI
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
azureFoundry/HuggingFace/microsoft-resnet-101@1
# ResNet-101 v1.5 ResNet model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) by He et al. Disclaimer: The team releasing ResNet did not write a model card for t
huggingface/microsoft/resnet-18
cloudflareWorkersAI/@cf/microsoft/resnet-50
50 layers deep image classification CNN trained on more than 1M images from ImageNet
- Input modalities
- image
- Capabilities
- visionInput
vertexAI/publishers/hf-microsoft/models/rho-math-1b-v0.1@001
Benchmarks
- LLM-Perf: 186,889,804.983
- Open LLM Leaderboard v1: 34.985%