• ALLaM

• AutoML

• Chat Completion

• Conversational

• Foundation Models

• llama

• Local

• meta

• MLflow Transformers

• Models

• OpenMMLab

• Phi

• Snowflake

• Text Generation

• ALLaM-2-7b-instruct

  Description

ALLaM is a series of powerful language models designed to advance Arabic Language Technology (ALT) developed by the National Center for Artificial Intelligence (NCAI) at the Saudi Data and AI Authority (SDAIA). ALLaM-2-7b-instruct is traine...

• Atomica

  ATOMICA is a hierarchical geometric deep learning model trained on over 2.1 million molecular interaction interfaces. It represents interaction complexes using an all-atom graph structure, where nodes correspond to atoms or grouped chemical blocks, and edges reflect both intra- and intermolecular...

• Aurora

  Aurora is a machine learning model that can predict general environmental variables, such as temperature and wind speed. It is a foundation model, which means that it was first generally trained on a lot of data, and then can be adapted to specialised environmental forecasting tasks with relati...

• AutoML-Image-Classification

  Automated Machine Learning, or AutoML, is a process that automates the repetitive and time-consuming tasks involved in developing machine learning models. This helps data scientists, analysts, and developers to create models more efficiently and with higher quality, resulting in increased product...

• AutoML-Image-Instance-Segmentation

  Automated Machine Learning, or AutoML, is a process that automates the repetitive and time-consuming tasks involved in developing machine learning models. This helps data scientists, analysts, and developers to create models more efficiently and with higher quality, resulting in increased product...

• AutoML-Image-Object-Detection

  Automated Machine Learning, or AutoML, is a process that automates the repetitive and time-consuming tasks involved in developing machine learning models. This helps data scientists, analysts, and developers to create models more efficiently and with higher quality, resulting in increased product...

• AutoML-Named-Entity-Recognition

  Automated Machine Learning, or AutoML, is a process that automates the repetitive and time-consuming tasks involved in developing machine learning models. This helps data scientists, analysts, and developers to create models more efficiently and with higher quality, resulting in increased product...

• AutoML-Text-Classification

  Automated Machine Learning, or AutoML, is a process that automates the repetitive and time-consuming tasks involved in developing machine learning models. This helps data scientists, analysts, and developers to create models more efficiently and with higher quality, resulting in increased product...

• bert-base-cased

  BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inpu...

• bert-base-uncased

  BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labeling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate input...

• bert-large-cased

  BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inpu...

• bert-large-uncased

  BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inpu...

• BiomedCLIP-PubMedBERT_256-vit_base_patch16_224

  BiomedCLIP is a biomedical vision-language foundation model that is pretrained on PMC-15M, a dataset of 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central, using contrastive learning. It uses PubMedBERT as the text encoder and Vision Transformer as the i...

• bytetrack_yolox_x_crowdhuman_mot17-private-half

  bytetrack_yolox_x_crowdhuman_mot17-private-half model is from OpenMMLab's MMTracking library. Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtai...

• camembert-base

  CamemBERT is a state-of-the-art language model for French based on the RoBERTa model.

It is now available on Hugging Face in 6 different versions with varying number of parameters, amount of pretraining data and pretraining data source domains.

OSCAR or Open...

• Cell2Sentence-Embedding

  Cell2Sentence (C2S) is a framework designed to apply Large Language Models (LLMs) to single-cell transcriptomics. It transforms single-cell RNA sequencing (scRNA-seq) data into a format that LLMs can natively understand. The core idea is to convert the gene expression vector of each cell into a "...

• compvis-stable-diffusion-v1-4

  Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. The Stable-Diffusion-v1-4 checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 225k steps at resolution 5...

• CxrReportGen

  Overview

The CXRReportGen model utilizes a multimodal architecture, integrating a BiomedCLIP image encoder with a Phi-3-Mini text encoder to help an application interpret complex medical imaging studies of chest X-rays. CXRReportGen follows the same framework as **[MAIRA-2](https://www.micros...

• databricks-dolly-v2-12b

  Databricks' dolly-v2-12b, an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use. Based on pythia-12b, Dolly is trained on ~15k instruction/response fine tuning records [databricks-dolly-15k](https://github.com/d...

• Deci-DeciCoder-1b

  The Model Card for DeciCoder 1B provides details about a 1 billion parameter decoder-only code completion model developed by Deci. The model was trained on Python, Java, and JavaScript subsets of Starcoder Training Dataset and uses Grouped Query Attention with a context window of 2048 tokens. It ...

• deci-decidiffusion-v1-0

  DeciDiffusion 1.0 is an 820 million parameter latent diffusion model designed for text-to-image conversion. Trained initially on the LAION-v2 dataset and fine-tuned on the LAION-ART dataset, the model's training involved advanced techniques to improve speed, training performance, and achieve su...

• Deci-DeciLM-7B

  DeciLM-7B is a decoder-only text generation model with 7.04 billion parameters, released by Deci under the Apache 2.0 license. It is the top-performing 7B base language model on the Open LLM Leaderboard and uses variable Grouped-Query Attention (GQA) to achieve a superior balance between accuracy...

• Deci-DeciLM-7B-instruct

  DeciLM-7B-instruct is a model for short-form instruction following, built by LoRA fine-tuning on the SlimOrca dataset. It is a derivative of the recently released DeciLM-7B language model, a pre-trained, high-efficiency generative text model with 7 billion parameters. DeciLM-7B-instruct is one of...

• deepseek-r1-distill-llama-8b

  This model is an optimized version of DeepSeek-R1-Distill-Llama-8B for local inference. Optimized models are published here in ONNX format to run on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of ...

• deepseek-r1-distill-llama-8b-cuda-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Llama-8B to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R...

• deepseek-r1-distill-llama-8b-generic-cpu

  This model is an optimized version of DeepSeek-R1-Distill-Llama-8B to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Dis...

• deepseek-r1-distill-llama-8b-generic-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Llama-8B to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Dis...

• deepseek-r1-distill-qwen-1.5b

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B for local inference. Optimized models are published here in ONNX format to run on CPU, GPU, and NPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to e...

• deepseek-r1-distill-qwen-1.5b-cuda-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-...

• deepseek-r1-distill-qwen-1.5b-generic-cpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Di...

• deepseek-r1-distill-qwen-1.5b-generic-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Di...

• DeepSeek-R1-Distill-Qwen-1.5B-openvino-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Distill-Qwen-1.5B for local in...

• deepseek-r1-distill-qwen-1.5b-qnn-npu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on QNN NPUs. This model uses QuaRot and GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of th...

• DeepSeek-R1-Distill-Qwen-1.5B-trtrtx-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on TensorRT-RTX GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Distill-Qwen-1.5B for l...

• deepseek-r1-distill-qwen-14b

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B for local inference. Optimized models are published here in ONNX format to run on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of ...

• deepseek-r1-distill-qwen-14b-cuda-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R...

• deepseek-r1-distill-qwen-14b-generic-cpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Dis...

• deepseek-r1-distill-qwen-14b-generic-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Dis...

• DeepSeek-R1-Distill-Qwen-14B-openvino-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Distill-Qwen-14B for local infe...

• deepseek-r1-distill-qwen-14b-qnn-npu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on QNN NPUs. This model uses QuaRot and GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the...

• deepseek-r1-distill-qwen-14b-trtrtx-gpu

  This model is an optimized version of deepseek-r1-distill-qwen-14b to enable local inference on TensorRT-RTX GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the deepseek-r1-distill-qwen-14b for loc...

• deepseek-r1-distill-qwen-7b

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference. Optimized models are published here in ONNX format to run on CPU, GPU, and NPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited ...

• deepseek-r1-distill-qwen-7b-cuda-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1...

• deepseek-r1-distill-qwen-7b-generic-cpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Dist...

• deepseek-r1-distill-qwen-7b-generic-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Dist...

• DeepSeek-R1-Distill-Qwen-7B-openvino-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Distill-Qwen-7B for local infere...

• DeepSeek-R1-Distill-Qwen-7B-openvino-npu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on Intel NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Distill-Qwen-7B for local infere...

• deepseek-r1-distill-qwen-7b-qnn-npu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on QNN NPUs. This model uses QuaRot and GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the ...

• DeepSeek-R1-Distill-Qwen-7B-trtrtx-gpu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on TensorRT-RTX GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Distill-Qwen-7B for local...

• DeepSeek-R1-Distill-Qwen-7B-vitis-npu

  This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on AMD NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the DeepSeek-R1-Distill-Qwen-7B for local inferenc...

• deepset-minilm-uncased-squad2

  Training Details

seed=42
batch_size = 12
n_epochs = 4
base_LM_model = "microsoft/MiniLM-L12-H384-uncased"
max_seq_len = 384
learning_rate = 4e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
grad_acc_steps=4

• deepset-roberta-base-squad2

  This is the roberta-base model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering.

• deformable_detr_twostage_refine_r50_16x2_50e_coco

  deformable_detr_twostage_refine_r50_16x2_50e_coco model is from OpenMMLab's MMDetection library. This model is reported to obtain <a href="https://github.com/open-mmlab/mmdetection/blob/e9cae2d0787cd5c2fc6165a6...

• distilbert-base-cased

  DistilBERT, a transformers model, is designed to be smaller and quicker than BERT. It underwent pretraining on the same dataset in a self-supervised manner, utilizing the BERT base model as a reference. This entails training solely on raw texts, without human annotation, thus enabling the utiliza...

• distilbert-base-cased-distilled-squad

  The DistilBERT model was proposed in the blog post Smaller, faster, cheaper, lighter: Introducing DistilBERT, adistilled version of BERT, and the paper [DistilBERT, adistilled version of BERT: smaller, faster, cheaper and lighter](https://...

• distilbert-base-uncased

  DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lot...

• distilbert-base-uncased-distilled-squad

  DistilBERT model was proposed in the blog post Smaller, faster, cheaper, lighter: Introducing DistilBERT, adistilled version of BERT, and the paper [DistilBERT, adistilled version of BERT: smaller, faster, cheaper and lighter](https://arxi...

• distilbert-base-uncased-finetuned-sst-2-english

  DistilBERT base uncased finetuned SST-2 model is a fine-tune checkpoint of DistilBERT-base-uncased, fine-tuned on SST-2. This model reaches an accuracy of 91.3 on the dev set (for comparison, Bert bert-base-uncased version reaches an accuracy ...

• distilgpt2

  DistilGPT2 (short for Distilled-GPT2) is an English-language model pre-trained with the supervision of the 124 million parameter version of GPT-2. DistilGPT2, which has 82 million parameters, was developed using knowledge distillation and was designed to be a faster, li...

• distilroberta-base

  distilroberta-base is a distilled version of the RoBERTa-base model. It follows the same training procedure as DistilBERT. The code for the distillation process can be found [here](https://github.com/hugg...

• facebook-bart-large-cnn

  BART is a transformer model that combines a bidirectional encoder similar to BERT with an autoregressive decoder akin to GPT. It is trained using two main techniques: (1) corrupting text with a chosen noising function, and (2) training a model to reconstruct the original text.

When fine-tuned fo...

• facebook-deit-base-patch16-224

  DeiT (Data-efficient image Transformers) is an image transformer that do not require very large amounts of data for training. This is achieved through a novel distillation procedure using teacher-student strategy, which results in high throughput and accuracy. DeiT is pre-trained and fine-tuned o...

• facebook-dinov2-base-imagenet1k-1-layer

  Vision Transformer (base-sized model) trained using DINOv2

Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper DINOv2: Learning Robust Visual Features without Supervision by Oquab et al. and first released...

• Facebook-DinoV2-Image-Embeddings-ViT-Base

  The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method.

Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also adds a [CLS] token ...

• Facebook-DinoV2-Image-Embeddings-ViT-Giant

  The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method.

Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also adds a [CLS] token ...

• facebook-sam-vit-base

  The Segment Anything Model (SAM) produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a dataset of 11 million images and 1.1 bi...

• facebook-sam-vit-huge

  The Segment Anything Model (SAM) produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a dataset of 11 million images and 1.1 bi...

• facebook-sam-vit-large

  The Segment Anything Model (SAM) produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a dataset of 11 million images and 1.1 bi...

• financial-reports-analysis

  Description

The adapted AI model for financial reports analysis (preview) is a state-of-the-art small language model (SLM) based on the Phi-3-small-128k architecture, designed specifically for analyzing financial reports. It has been fine-tuned on a few hundred million tokens derived ...

• financial-reports-analysis-v2

The Adapted AI model for financial reports analysis (Phi-4, preview) is a state-of-the-art small language model (SLM) based on the Phi-4 architecture, de...

• finiteautomata-bertweet-base-sentiment-analysis

  Repository: https://github.com/finiteautomata/pysentimiento/

Model trained with SemEval 2017 corpus (around ~40k tweets). Base model is BERTweet, a RoBERTa model trained on English tweets.

Uses `POS...

• google-vit-base-patch16-224

  The Vision Transformer (ViT) model, as introduced in the paper "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale" by Dosovitskiy et al., underwent pre-training on ImageNet-21k with a resolution of 224x224. Su...

• gpt-oss-20b-generic-cpu

  This model is an optimized version of gpt-oss-20b to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: Apache-2.0

• License Description: Use of this model is subject to the terms of the Ap...

• gpt-oss-20b-generic-gpu

  This model is an optimized version of gpt-oss-20b to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: Apache-2.0

• License Description: Use of this model is subject to the terms of the Ap...

• gpt2

  GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generat...

• gpt2-large

  GPT-2 Large is the 774M parameter version of GPT-2, a transformer-based language model created and released by OpenAI. The model is a pretrained model on English language using a causal language modeling (CLM)

See the [associated paper](https://d4mucfpksywv.cloudfront.net/bet...

• gpt2-medium

  GPT-2 Medium is the 355M parameter version of GPT-2, a transformer-based language model created and released by OpenAI. The model is a pretrained model on English language using a causal language modeling (CLM) objective.

See the [associated paper](https://d4mucfpksywv.c...

• hibou-b

  Hibou-B is a foundational vision transformer developed for digital pathology, designed to generate high-quality feature representations from histology image patches. These representations can be leveraged for a range of downstream tasks, including classification, segmentation, and detection.

Bui...

• hibou-l

  Hibou-L is a foundational vision transformer developed for digital pathology, designed to generate high-quality feature representations from histology image patches. These representations can be leveraged for a range of downstream tasks, including classification, segmentation, and detection.

Bui...

• Jean-Baptiste-camembert-ner

  Summary: camembert-ner is a NER model fine-tuned from camemBERT on the Wikiner-fr dataset and was validated on email/chat data. It shows better performance on entities that do not start with an uppercase. The model has four classes: O, MISC, PER, ORG and LOC. The model can be loaded using Hugging...

• Llama-2-13b

  Meta has developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. L...

• Llama-2-13b-chat

  Meta has developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. L...

• Llama-2-70b

  Meta has developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. L...

• Llama-2-70b-chat

  Meta has developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. L...

• Llama-2-7b

  Meta has developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. L...

• Llama-2-7b-chat

  Meta has developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. L...

• mask_rcnn_swin-t-p4-w7_fpn_1x_coco

  This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual ...

• MatterSim

  MatterSim is a large-scale pretrained deep learning model for efficient materials emulations and property predictions.

MatterSim is a deep learning model for general materials design tasks. It supports efficient atomistic simulations at first-principles level and accurate prediction of broad mat...

• MedImageInsight

  Most medical imaging AI today is narrowly built to detect a small set of individual findings on a single modality like chest X-rays. This training approach is data- and computationally inefficient, requiring ~6-12 months per finding1, and often fails to generalize in real world environments. By f...

• MedImageInsight-onnx

  Most medical imaging AI today is narrowly built to detect a small set of individual findings on a single modality like chest X-rays. This training approach is data- and computationally inefficient, requiring ~6-12 months per finding[1], and often fails to generalize in real world environments. By...

• MedImageParse

  Biomedical image analysis is fundamental for biomedical discovery in cell biology, pathology, radiology, and many other biomedical domains. MedImageParse is a biomedical foundation model for imaging parsing that can jointly conduct segmentation, detection, and recognition across 9 imaging modalit...

• MedImageParse3D

Biomedical image analysis is fundamental for biomedical discovery in cell biology, pathology, radiology, and many other biomedical domains. 3D medical images such...

• MedSAM2

  MedSAM2 is a breakthrough medical image segmentation foundation model that addresses the critical need for efficient and accurate segmentation in precision medicine. Built upon the Segment Anything Model (SAM) 2.1 architecture, it uniquely bridges the gap between 2D and 3D medical image segmentat...

• MedVAE-8-4-2d

  MedVAE is a family of large-scale, generalizable 2D and 3D variational autoencoders (VAEs) designed to address critical efficiency and storage challenges in medical imaging. Trained on over one million images across multiple modalities and anatomical regions, MedVAE excels at encoding high-resolu...

• microsoft-beit-base-patch16-224-pt22k-ft22k

  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 then fine-tuned f...

• microsoft-deberta-base

  DeBERTa (Decoding-enhanced BERT with Disentangled Attention) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data...

• microsoft-deberta-base-mnli

  DeBERTa (Decoding-enhanced BERT with Disentangled Attention) 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 data.

Please check the [offi...

• microsoft-deberta-large

  DeBERTa (Decoding-enhanced BERT with Disentangled Attention) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data...

• microsoft-deberta-large-mnli

  DeBERTa (Decoding-enhanced BERT with Disentangled Attention) 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 data.

Please check the [offi...

• microsoft-deberta-xlarge

  DeBERTa (Decoding-enhanced BERT with Disentangled Attention) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data...

• microsoft-llava-med-v1.5-mistral-7b

  LLaVA-Med v1.5, using mistralai/Mistral-7B-Instruct-v0.2 as LLM for a better commercial license

Large Language and Vision Assistant for bioMedicine (i.e., “LLaVA-Med”) is a large language and vision model trained using a curriculum l...

• microsoft-Orca-2-13b

  Orca 2 is a finetuned version of LLAMA-2. Orca 2’s training data is a synthetic dataset that was created to enhance the small model’s reasoning abilities. All synthetic training data was moderated using the Microsoft Azure content filters. More details about the model can be found in the [Orca 2 ...

• microsoft-Orca-2-7b

  Orca 2 is a finetuned version of LLAMA-2. Orca 2’s training data is a synthetic dataset that was created to enhance the small model’s reasoning abilities. All synthetic training data was moderated using the Microsoft Azure content filters. More details about the model can be found in the [Orca 2 ...

• microsoft-phi-1-5

  Microsoft Phi-1.5

Phi-1.5 is a Transformer-based language model with 1.3 billion parameters. It was trained on a combination of data sources, including an additional source of NLP synthetic texts. Phi-1.5 performs exceptionally well on benchmarks testing common sense, language understandi...

• microsoft-phi-2

  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 value). When assesse...

• microsoft-rad-dino

  Model Description

RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method DINOv2.

RAD-DINO is described in detail in [RAD-DINO: Exploring Sca...

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

  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 research-paper titled "Swin Transformer V2: Scaling Up Capacity and Resolution" authored by ...

• ministral-3-3b-instruct-2512

  This model is an optimized version of Ministral-3-3B-Instruct-2512 for local inference. Optimized models are published here in ONNX format to run on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of ...

• ministral-3-3b-instruct-2512-cuda-gpu

  This model is an optimized version of Ministral-3-3B-Instruct-2512 for local inference on CUDA GPUs. This optimized model is published here in ONNX format to run on CUDA-capable GPU devices, with the precision best suited to this target.

Here are some of the optimized configuration...

• ministral-3-3b-instruct-2512-generic-cpu

  This model is an optimized version of Ministral-3-3B-Instruct-2512 for local inference on CPU and mobile devices. This optimized model is published here in ONNX format to run on CPU and mobile targets, with the precision best suited to this target.

Here are some of the optimized co...

• ministral-3-3b-instruct-2512-generic-gpu

  This model is an optimized version of Ministral-3-3B-Instruct-2512 for local inference on WebGPU-capable devices. This optimized model is published here in ONNX format to run with the WebGPU execution provider, with the precision best suited to this target.

Here are some of the opt...

• Mistral-7B-Instruct-v0-2-openvino-gpu

  This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mistral-7B-Instruct-v0.2 for local infer...

• Mistral-7B-Instruct-v0-2-openvino-npu

  This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on Intel NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mistral-7B-Instruct-v0.2 for local infer...

• Mistral-7B-Instruct-v0-2-vitis-npu

  This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on AMD NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mistral-7B-Instruct-v0.2 for local inferen...

• mistral-community-Mixtral-8x22B-v0-1

  The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

Mixtral-8x22B-v0.1 is a pretrained base model and therefore does not have any moderation mechanisms.

[Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/H...

• mistral-nemo-12b-instruct

  This model is an optimized version of Mistral-Nemo-Instruct-2407 for local inference. Optimized models are published here in ONNX format to run on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of th...

• mistral-nemo-12b-instruct-cuda-gpu

  This model is an optimized version of Mistral-Nemo-Instruct-2407 to enable local inference on CUDA GPUs. This model uses GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mist...

• mistral-nemo-12b-instruct-generic-cpu

  This model is an optimized version of Mistral-Nemo-Instruct-2407 to enable local inference on CPUs. This model uses GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mistral-N...

• mistral-nemo-12b-instruct-generic-gpu

  This model is an optimized version of Mistral-Nemo-Instruct-2407 to enable local inference on GPUs. This model uses GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mistral-N...

• mistralai-Mistral-7B-Instruct-v0-2

  The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.

Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1:

• 32k context window (vs 8k context in v0.1)
• Rope-theta = 1e6
• No Sliding-Window Attention

For full details...

• mistralai-Mistral-7B-Instruct-v0-2-cuda-gpu

  This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mistral...

• mistralai-Mistral-7B-Instruct-v0-2-generic-cpu

  This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: apache-2.0

• License: MIT

• Model Description: This is a conversion of the Mistral-7B-In...

• mistralai-Mistral-7B-Instruct-v0-2-generic-gpu

  This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mistral-7B-I...

• mistralai-Mistral-7B-Instruct-v0-2-trtrtx-gpu

  This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on TensorRT-RTX GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Mistral-7B-Instruct-v0.2 for loc...

• mistralai-Mistral-7B-Instruct-v0-3

  The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3.

Mistral-7B-v0.3 has the following changes compared to Mistral-7B-v0.2

• Extended vocabulary to 32768 ...

• mistralai-Mistral-7B-Instruct-v01

  Model Details

The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.

For full details of this mod...

• mistralai-Mistral-7B-v01

  Model Details

The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks tested.

For full details of this model please read paper and [releas...

• mistralai-Mixtral-8x22B-Instruct-v0-1

  The Mixtral-8x22B-Instruct-v0.1 Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B-v0.1.

• mistralai-Mixtral-8x22B-v0-1

  The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

Mixtral-8x22B-v0.1 is a pretrained base model and therefore does not have any moderation mechanisms.

[Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/H...

• mistralai-Mixtral-8x7B-Instruct-v01

  The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks with 6x faster inference.

Mixtral-8x7B-v0.1 is a decoder-only model with 8 distinct groups or the "experts". At every layer, for every tok...

• mistralai-Mixtral-8x7B-v01

  Model Details

The Mixtral-8x7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mixtral-8x7B-v0.1 outperforms Llama 2 70B on most benchmarks with 6x faster inference.

For full details of this model please read [release blog post](https://mi...

• mmd-3x-deformable-detr_refine_twostage_r50_16xb2-50e_coco

  deformable-detr_refine_twostage_r50_16xb2-50e_coco model is from OpenMMLab's MMDetection library. DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while...

• mmd-3x-mask-rcnn_swin-t-p4-w7_fpn_1x_coco

  mask-rcnn_swin-t-p4-w7_fpn_1x_coco model is from OpenMMLab's MMDetection library. This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for comp...

• mmd-3x-rtmdet-ins_x_8xb16-300e_coco

  rtmdet-ins_x_8xb16-300e_coco model is from OpenMMLab's MMDetection library. In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many o...

• mmd-3x-sparse-rcnn_r101_fpn_300-proposals_crop-ms-480-800-3x_coco

  sparse-rcnn_r101_fpn_300-proposals_crop-ms-480-800-3x_coco model is from OpenMMLab's MMDetection library. We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object ...

• mmd-3x-sparse-rcnn_r50_fpn_300-proposals_crop-ms-480-800-3x_coco

  sparse-rcnn_r50_fpn_300-proposals_crop-ms-480-800-3x_coco model is from OpenMMLab's MMDetection library. We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object d...

• mmd-3x-vfnet_r50-mdconv-c3-c5_fpn_ms-2x_coco

  vfnet_r50-mdconv-c3-c5_fpn_ms-2x_coco model is from OpenMMLab's MMDetection library. Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. ...

• mmd-3x-vfnet_x101-64x4d-mdconv-c3-c5_fpn_ms-2x_coco

  vfnet_x101-64x4d-mdconv-c3-c5_fpn_ms-2x_coco model is from OpenMMLab's MMDetection library. Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high perfor...

• mmd-3x-yolof_r50_c5_8x8_1x_coco

  yolof_r50_c5_8x8_1x_coco model is from OpenMMLab's MMDetection library. This paper revisits feature pyramids networks (FPN) for one-stage detectors and points out that the success of FPN is due to its divide-an...

• mmeft

  Multimodal Early Fusion Transformer (MMEFT) is a transformer-based model tailored for processing both structured and unstructured data.

It can be used for multi-class and multi-label multimodal classification tasks, and is capable of handling datasets with features from diverse modes, includ...

• nemotron-3.5-asr-streaming-0.6b

  This model is an optimized version of nemotron-3.5-asr-streaming-0.6b for local inference. Optimized models are published here in ONNX format to run on CPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs.

• Developed by: Micros...

• nemotron-3.5-asr-streaming-0.6b-cuda-gpu

  This model is an optimized version of nemotron-3.5-asr-streaming-0.6b to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is an optimized version of the nem...

• nemotron-3.5-asr-streaming-0.6b-generic-cpu

  This model is an optimized version of nemotron-3.5-asr-streaming-0.6b to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is an optimized version of the nem...

• nemotron-speech-streaming-en-0.6b

  This model is an optimized version of nemotron-speech-streaming-en-0.6b for local inference. Optimized models are published here in ONNX format to run on CPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs.

• Developed by: Micr...

• nemotron-speech-streaming-en-0.6b-cuda-gpu

  This model is an optimized version of nemotron-speech-streaming-en-0.6b to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is an optimized version of the n...

• nemotron-speech-streaming-en-0.6b-generic-cpu

  This model is an optimized version of nemotron-speech-streaming-en-0.6b to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is an optimized version of the n...

• nemotron-speech-streaming-es-0.6b-ft-cuda-gpu

  This model is a fine-tuned and optimized derivative of nemotron-speech-streaming-en-0.6b, adapted for Spanish speech recognition. The model is optimized for local inference on GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• **Model Descri...

• nemotron-speech-streaming-es-0.6b-ft-generic-cpu

  This model is a fine-tuned and optimized derivative of nemotron-speech-streaming-en-0.6b, adapted for Spanish speech recognition. The model is optimized for local inference.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description:...

• ocsort_yolox_x_crowdhuman_mot17-private-half

  ocsort_yolox_x_crowdhuman_mot17-private-half model is from OpenMMLab's MMTracking library. Multi-Object Tracking (MOT) has rapidly progressed with the development of object detection and re-identification. Howev...

• olmo-3-7b-instruct

  This model is an optimized version of Olmo-3-7B-Instruct for local inference. Optimized models are published here in ONNX format to run on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targ...

• olmo-3-7b-instruct-cuda-gpu

  This model is an optimized version of Olmo-3-7B-Instruct to enable local inference on CUDA GPUs. This model uses GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Olmo-3-7B-In...

• olmo-3-7b-instruct-generic-cpu

  This model is an optimized version of Olmo-3-7B-Instruct to enable local inference on CPUs. This model uses GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Olmo-3-7B-Instruc...

• olmo-3-7b-instruct-generic-gpu

  This model is an optimized version of Olmo-3-7B-Instruct to enable local inference on GPUs. This model uses GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: apache-2.0

• Model Description: This is a conversion of the Olmo-3-7B-Instruc...

• OpenAI-CLIP-Image-Text-Embeddings-vit-base-patch32

  OpenAI's CLIP (Contrastive Language–Image Pre-training) model was designed to investigate the factors that contribute to the robustness of computer vision tasks. It can seamlessly adapt to a range of image classification tasks without requiring specific training for each, demonstrating efficiency...

• OpenAI-CLIP-Image-Text-Embeddings-ViT-Large-Patch14-336

  The CLIP model was developed by researchers at OpenAI to learn about what contributes to robustness in computer vision tasks. The model was also developed to test the ability of models to generalize to arbitrary image classification tasks in a zero-shot manner. It was not developed for general ...

• openai-clip-vit-base-patch32

  OpenAI's CLIP (Contrastive Language–Image Pre-training) model was designed to investigate the factors that contribute to the robustness of computer vision tasks. It can seamlessly adapt to a range of image classification tasks without requiring specific training for each, demonstrating efficiency...

• openai-clip-vit-large-patch14

  OpenAI's CLIP (Contrastive Language–Image Pre-training) model was designed to investigate the factors that contribute to the robustness of computer vision tasks. It can seamlessly adapt to a range of image classification tasks without requiring specific training for each, demonstrating efficiency...

• openai-whisper-base

  This model is an optimized version of Whisper Base for local inference. Optimized models are published here in ONNX format to run on CPU, GPU, and NPU across devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original...

• openai-whisper-base-cuda-gpu

  This model is an optimized version of Whisper Base for local inference. Optimized models are published here in ONNX format to run on CUDA devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original model card](https:/...

• openai-whisper-base-generic-cpu

  This model is an optimized version of Whisper Base for local inference. Optimized models are published here in ONNX format to run on CPU devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original model card](https://...

• openai-whisper-large

  Whisper is an OpenAI pre-trained speech recognition model with potential applications for ASR solutions for developers. However, due to weak supervision and large-scale noisy data, it should be used with caution in high-risk domains. The model has been trained on 680k hours of audio data represen...

• openai-whisper-large-v3

  Whisper is a model that can recognize and translate speech using deep learning. It was trained on a large amount of data from different sources and languages. Whisper models can handle various tasks and domains without needing to adjust the model.

Whisper large-v3 is similar to the previous larg...

• openai-whisper-large-v3-turbo

  This model is an optimized version of Whisper Large V3 Turbo for local inference. Optimized models are published here in ONNX format to run on CPU, GPU, and NPU across devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the...

• openai-whisper-large-v3-turbo-cuda-gpu

  Whisper Large V3 Turbo is an advanced speech recognition model, optimized for high-performance GPU inference. It is suitable for automatic speech recognition (ASR) tasks in various domains, leveraging large-scale training data for robust multilingual transcription. This model is an optimized vers...

• openai-whisper-large-v3-turbo-generic-cpu

  Whisper Large V3 Turbo is an advanced speech recognition model, optimized for high-performance CPU inference. It is suitable for automatic speech recognition (ASR) tasks in various domains, leveraging large-scale training data for robust multilingual transcription. This model is designed for scen...

• openai-whisper-medium

  This model is an optimized version of Whisper Medium for local inference. Optimized models are published here in ONNX format to run on CPU, GPU, and NPU across devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [origin...

• openai-whisper-medium-cuda-gpu

  This model is an optimized version of Whisper Medium for local inference. Optimized models are published here in ONNX format to run on CUDA devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original model card](https...

• openai-whisper-medium-generic-cpu

  This model is an optimized version of Whisper Medium for local inference. Optimized models are published here in ONNX format to run on CPU devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original model card](https:...

• openai-whisper-small

  This model is an optimized version of Whisper Small for local inference. Optimized models are published here in ONNX format to run on CPU, GPU, and NPU across devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [origina...

• openai-whisper-small-cuda-gpu

  This model is an optimized version of Whisper Small for local inference. Optimized models are published here in ONNX format to run on CUDA devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original model card](https:...

• openai-whisper-small-generic-cpu

  This model is an optimized version of Whisper Small for local inference. Optimized models are published here in ONNX format to run on CPU devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original model card](https:/...

• openai-whisper-tiny

  This model is an optimized version of Whisper Tiny for local inference. Optimized models are published here in ONNX format to run on CPU, GPU, and NPU across devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original...

• openai-whisper-tiny-cuda-gpu

  This model is an optimized version of Whisper Tiny for local inference. Optimized models are published here in ONNX format to run on CUDA devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original model card](https:/...

• openai-whisper-tiny-generic-cpu

  This model is an optimized version of Whisper Tiny for local inference. Optimized models are published here in ONNX format to run on CPU devices, including server platforms, desktops, and mobile, with the precision best suited to each of these targets.

Review the [original model card](https://...

• parakeet-tdt-0.6b-v2

  This model is an optimized version of parakeet-tdt-0.6b-v2 for local inference. Optimized models are published here in ONNX format to run on CPU and CUDA GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs.

• Developed by: Micr...

• parakeet-tdt-0.6b-v2-cuda-gpu

  This model is an optimized version of parakeet-tdt-0.6b-v2 for local inference on CUDA GPUs. This optimized model is published here in ONNX format to run on CUDA-capable GPU devices, with the precision best suited to this target.

• Developed by: Microsoft

• **Model type:*...

• parakeet-tdt-0.6b-v2-generic-cpu

  This model is an optimized version of parakeet-tdt-0.6b-v2 for local inference. Optimized models are published here in ONNX format to run on CPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs.

• Developed by: Microsoft

• **Mod...

• Phi-3-medium-128k-instruct

  The Phi-3-Medium-128K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Ph...

• Phi-3-medium-4k-instruct

  The Phi-3-Medium-4K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-...

• Phi-3-mini-128k-instruct

  The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties.

After initi...

• Phi-3-mini-128k-instruct-cuda-gpu

  This model is an optimized version of Phi-3-Mini-128K-Instruct to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-128...

• Phi-3-mini-128k-instruct-generic-cpu

  This model is an optimized version of Phi-3-Mini-128K-Instruct to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-128K-Ins...

• Phi-3-mini-128k-instruct-generic-gpu

  This model is an optimized version of Phi-3-Mini-128K-Instruct to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-128K-Ins...

• Phi-3-mini-128k-instruct-openvino-gpu

  This model is an optimized version of Phi-3-Mini-128K-Instruct to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-128K-Instruct for local inference on...

• phi-3-mini-128k-instruct-qnn-npu

  This model is an optimized version of phi-3-mini-128k-instruct to enable local inference on QNN NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the phi-3-mini-128k-instruct for local inference on Q...

• phi-3-mini-128k-instruct-trtrtx-gpu

  This model is an optimized version of phi-3-mini-128k-instruct to enable local inference on TensorRT-RTX GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the phi-3-mini-128k-instruct for local infer...

• phi-3-mini-128k-instruct-vitis-npu

  This model is an optimized version of Phi-3-mini-128k-instruct to enable local inference on AMD NPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-mini-128k...

• Phi-3-mini-4k-instruct

  The Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3...

• Phi-3-mini-4k-instruct-cuda-gpu

  This model is an optimized version of Phi-3-Mini-4K-Instruct to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-4K-In...

• Phi-3-mini-4k-instruct-generic-cpu

  This model is an optimized version of Phi-3-Mini-4K-Instruct to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-4K-Instruc...

• Phi-3-mini-4k-instruct-generic-gpu

  This model is an optimized version of Phi-3-Mini-4K-Instruct to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-4K-Instruc...

• Phi-3-mini-4k-instruct-openvino-gpu

  This model is an optimized version of Phi-3-Mini-4K-Instruct to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-4K-Instruct for local inference on Int...

• Phi-3-mini-4k-instruct-openvino-npu

  This model is an optimized version of Phi-3-Mini-4K-Instruct to enable local inference on Intel NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-4K-Instruct for local inference on Int...

• phi-3-mini-4k-instruct-qnn-npu

  This model is an optimized version of phi-3-mini-4k-instruct to enable local inference on QNN NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the phi-3-mini-4k-instruct for local inference on QNN N...

• phi-3-mini-4k-instruct-trtrtx-gpu

  This model is an optimized version of phi-3-mini-4k-instruct to enable local inference on TensorRT-RTX GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the phi-3-mini-4k-instruct for local inference...

• Phi-3-mini-4k-instruct-vitis-npu

  This model is an optimized version of Phi-3-Mini-4K-Instruct to enable local inference on AMD NPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3-Mini-4K-Ins...

• Phi-3-small-128k-instruct

  The Phi-3-Small-128K-Instruct is a 7B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model supports 128K conte...

• Phi-3-small-8k-instruct

  The Phi-3-Small-8K-Instruct is a 7B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model supports 8K context l...

• Phi-3-vision-128k-instruct

  Model Summary

Phi-3 Vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 mo...

• Phi-3.5-mini-instruct

  Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. Th...

• Phi-3.5-mini-instruct-cuda-gpu

  This model is an optimized version of Phi-3.5-mini-instruct to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3.5-mini-inst...

• Phi-3.5-mini-instruct-generic-cpu

  This model is an optimized version of Phi-3.5-mini-instruct to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3.5-mini-instruct ...

• Phi-3.5-mini-instruct-generic-gpu

  This model is an optimized version of Phi-3.5-mini-instruct to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3.5-mini-instruct ...

• Phi-3.5-mini-instruct-openvino-gpu

  This model is an optimized version of Phi-3.5-Mini-Instruct to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3.5-Mini-Instruct for local inference on Intel...

• phi-3.5-mini-instruct-qnn-npu

  This model is an optimized version of phi-3.5-mini-instruct to enable local inference on QNN NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the phi-3.5-mini-instruct for local inference on QNN NPU...

• phi-3.5-mini-instruct-trtrtx-gpu

  This model is an optimized version of Phi-3.5-mini-instruct to enable local inference on TensorRT-RTX GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-3.5-mini-instruct for local inference o...

• Phi-3.5-MoE-instruct

  Phi-3.5-MoE is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available documents - with a focus on very high-quality, reasoning dense data. The model supports multilingual and comes with 128K context length (in tokens). The mo...

• Phi-3.5-vision-instruct

  Phi-3.5-vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 model family, and t...

• Phi-4

  Phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced r...

• Phi-4-cuda-gpu

  This model is an optimized version of Phi-4 to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4 for local inference on CUDA...

• Phi-4-generic-cpu

  This model is an optimized version of Phi-4 to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4 for local inference on CPUs.

• *...

• Phi-4-generic-gpu

  This model is an optimized version of Phi-4 to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4 for local inference on GPUs.

• *...

• Phi-4-mini-instruct-cuda-gpu

  This model is an optimized version of Phi-4-mini-instruct to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-instruct...

• Phi-4-mini-instruct-generic-cpu

  This model is an optimized version of Phi-4-mini-instruct to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-instruct for ...

• Phi-4-mini-instruct-generic-cpu-dq44

  This model is an optimized version of Phi-4-mini-instruct to enable local inference on CPUs. This model uses DiscQuant quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-instruc...

• Phi-4-mini-instruct-generic-gpu

  This model is an optimized version of Phi-4-mini-instruct to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-instruct for ...

• phi-4-mini-instruct-openvino-gpu

  This model is an optimized version of Phi-4-mini-instruct to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-instruct for local inference on Intel GPU...

• phi-4-mini-instruct-openvino-npu

  This model is an optimized version of Phi-4-mini-instruct to enable local inference on Intel NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-instruct for local inference on Intel NPU...

• phi-4-mini-instruct-vitis-npu

  This model is an optimized version of Phi-4-mini-instruct to enable local inference on AMD NPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-instruct ...

• Phi-4-mini-reasoning-cuda-gpu

  This model is an optimized version of Phi-4-mini-reasoning to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-reasoni...

• Phi-4-mini-reasoning-generic-cpu

  This model is an optimized version of Phi-4-mini-reasoning to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-reasoning fo...

• Phi-4-mini-reasoning-generic-gpu

  This model is an optimized version of Phi-4-mini-reasoning to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-reasoning fo...

• Phi-4-mini-reasoning-openvino-gpu

  This model is an optimized version of Phi-4-mini-reasoning to enable local inference on Intel GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-reasoning for local inference on Intel GP...

• Phi-4-mini-reasoning-openvino-npu

  This model is an optimized version of Phi-4-mini-reasoning to enable local inference on Intel NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-reasoning for local inference on Intel NP...

• Phi-4-mini-reasoning-qnn-npu

  This model is an optimized version of Phi-4-mini-reasoning to enable local inference on QNN NPUs. This model uses QuaRot and GPTQ quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-m...

• Phi-4-mini-reasoning-vitis-npu

  This model is an optimized version of Phi-4-mini-reasoning to enable local inference on AMD NPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-mini-reasoning for local inference on AMD NPUs. ...

• phi-4-openvino-gpu

  This model is an optimized version of Phi-4 to enable local inference on Intel GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4 for local inference on Int...

• Phi-4-reasoning-cuda-gpu

  This model is an optimized version of Phi-4-reasoning to enable local inference on CUDA GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-reasoning for loc...

• Phi-4-reasoning-generic-cpu

  This model is an optimized version of Phi-4-reasoning to enable local inference on CPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-reasoning for local in...

• Phi-4-reasoning-generic-gpu

  This model is an optimized version of Phi-4-reasoning to enable local inference on GPUs. This model uses RTN quantization.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4-reasoning for local in...

• Phi-4-trtrtx-gpu

  This model is an optimized version of Phi-4 to enable local inference on TensorRT-RTX GPUs.

• Developed by: Microsoft

• Model type: ONNX

• License: MIT

• Model Description: This is a conversion of the Phi-4 for local inference on TensorRT-RTX GPUs.

• **Disclai...

• Prism

  PRISM is a multi-modal generative foundation model for slide-level analysis of H&E-stained histopathology images. Utilizing Virchow tile embeddings and clinical report texts for pre-training, PRISM combines these embeddings into a single slide embedding and generates a text-based diagnostic repor...

• projecte-aina-aguila-7b

  Model Description