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-dayhoff-170m-ur50-brn@5
# Model Card for `microsoft/Dayhoff-170m-UR50-BRn` 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 sequenc
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-dayhoff-170m-ur50-brq@2
# Model Card for microsoft/Dayhoff-170m-UR50-BRq 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 sequence
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-dayhoff-170m-ur50-bru@1
`microsoft/Dayhoff-170m-UR50-BRu` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/Dayhoff-170m-UR50-BRu) ### Send Request You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-dayhoff-170m-ur90@1
`microsoft/Dayhoff-170m-UR90` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/Dayhoff-170m-UR90) ### 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
azureFoundry/HuggingFace/microsoft-dayhoff-3b-gr-hm@1
`microsoft/Dayhoff-3b-GR-HM` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/Dayhoff-3b-GR-HM) ### Send Request You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token. ```bash cu
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-dayhoff-3b-gr-hm-c@4
# Model Card for microsoft/Dayhoff-3b-GR-HM-c 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 (
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-dayhoff-3b-ur90@5
# Model Card for `microsoft/Dayhoff-3b-UR90` 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 (Gi
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-deberta-base@14
`microsoft/deberta-base` 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, you c
azureFoundry/HuggingFace/microsoft-deberta-base-mnli@5
## DeBERTa: Decoding-enhanced BERT with Disentangled Attention [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outperforms BERT and RoBERTa on majority of NLU tasks with 80GB training d
azureFoundry/HuggingFace/microsoft-deberta-large@10
## DeBERTa: Decoding-enhanced BERT with Disentangled Attention [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outperforms BERT and RoBERTa on majority of NLU tasks with 80GB training d
azureFoundry/HuggingFace/microsoft-deberta-large-mnli@9
## DeBERTa: Decoding-enhanced BERT with Disentangled Attention [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outperforms BERT and RoBERTa on majority of NLU tasks with 80GB training d
azureFoundry/HuggingFace/microsoft-deberta-v2-xlarge@12
`microsoft/deberta-v2-xlarge` 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-deberta-v2-xlarge-mnli@3
`microsoft/deberta-v2-xlarge-mnli` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text-classification` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitation
azureFoundry/HuggingFace/microsoft-deberta-v2-xxlarge@12
## DeBERTa: Decoding-enhanced BERT with Disentangled Attention [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outperforms BERT and RoBERTa on majority of NLU tasks with 80GB training d
azureFoundry/HuggingFace/microsoft-deberta-v2-xxlarge-mnli@6
## DeBERTa: Decoding-enhanced BERT with Disentangled Attention [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outperforms BERT and RoBERTa on majority of NLU tasks with 80GB training d
huggingface/microsoft/deberta-v3-base
huggingface/microsoft/deberta-v3-large
huggingface/microsoft/deberta-v3-small