Indian Flag
Government Of India
A-
A
A+
UpvoteUpvote
0

MAIRA-2 - Multimodal AI for Radiology Report Generation

A multimodal Transformer model designed for generating grounded and non-grounded radiology reports from chest X-rays, integrating vision and language understanding for medical AI research.
  • Upvotes0upvotes
  • Downloads33downloads
  • Views1,325views
  • File size0
  • Shares0Shares
  • Last updatedupdated 06 Nov 2026
UpvoteUpvote
0
LICENSE Other
SECTOR Healthcare, Wellness and Family Welfare

About Model

MAIRA-2 is a multimodal Transformer model developed by Microsoft Research Health Futures for automated radiology report generation. It processes chest X-ray images and generates structured reports, with or without grounding, by linking findings to specific image regions. The model is built using the RAD-DINO-MAIRA-2 image encoder and the Vicuna-7b-V1.5 language model, enabling advanced medical text generation. MAIRA-2 is intended for research purposes only and is not suitable for clinical practice due to potential biases and limitations in generalizability. Trained on datasets such as MIMIC-CXR, PadChest, and USMix, it aims to facilitate comparative studies in AI-driven radiology analysis. The model supports findings generation, phrase grounding, and structured medical text generation, providing valuable insights into automated medical imaging interpretation while promoting fairness and responsible AI use in healthcare.

Metadata Metadata

Other

Healthcare, Wellness and Family Welfare

Microsoft Health Futures

N.A.

Vikram Malhotra

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

Open

20/08/25 05:47:02

N.A.

0

Tags

  • Transformers
  • safetensors
  • Text Generation
  • conversational
  • maira2
  • custom_code

Related Models Related Models

microsoft/Phi-3-vision-128k-instruct
Phi-3-vision-128k-instruct is a state-of-the-art multimodal model by Microsoft, designed to process both text and visual inputs with a context length of up to 128,000 tokens.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads12
  • Views283
  • File Size0

Phi-3-Medium-4K-Instruct - Scalable AI Model for Reasoning and Code Generation
A 14B parameter AI model optimized for 4K and 128K token context lengths, designed for advanced reasoning, math, and coding applications, supporting both research and commercial use.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads0
  • Views270
  • File Size0

BiomedBERT - Domain-Specific Biomedical Language Model
A biomedical NLP model pre-trained from scratch on abstracts and full-text articles from PubMed and PubMed Central, achieving state-of-the-art performance on biomedical language understanding tasks.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads102
  • Views1,996
  • File Size0

Phi-3-Medium-128K-Instruct ONNX-CUDA - Optimized AI Model for NVIDIA GPU Inference
An ONNX-optimized version of Phi-3-Medium-128K-Instruct, designed for high-speed, efficient inference on NVIDIA GPUs, supporting FP16 and INT4 quantization for enhanced performance.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads2
  • Views168
  • File Size0

Phi-3-Small-8K-Instruct ONNX-CUDA - Optimized AI Model for NVIDIA GPU Inference
An ONNX-optimized version of Phi-3-Small-8K-Instruct, designed for efficient inference on NVIDIA GPUs, supporting FP16 and INT4 quantization for fast, scalable AI applications.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads1
  • Views174
  • File Size0

Phi-3-Mini-4K-Instruct GGUF - Optimized AI Model for GGUF Inference
A GGUF-optimized version of Phi-3-Mini-4K-Instruct, designed for efficient low-memory AI inference, supporting quantized and full-precision formats for balanced performance and quality.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters1
  • Downloads29
  • Views1,580
  • File Size0

Phi-3-Medium-128K-Instruct - Advanced Long-Context AI for Code and Logical Reasoning
A 14B parameter AI model optimized for 128K token context length, designed for complex reasoning, mathematical problem-solving, and efficient AI applications in commercial and research environments.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads3
  • Views133
  • File Size0

Phi-3-Medium-128K-Instruct ONNX-CPU - Optimized AI Model for CPU Inference
An ONNX-optimized version of Phi-3-Medium-128K-Instruct, designed for efficient long-context inference on CPUs, supporting structured reasoning, text generation, and code processing.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads2
  • Views212
  • File Size0

Phi-3-Mini-128K-Instruct ONNX - Optimized AI Model for Long-Context ONNX Inference
An ONNX-optimized version of Phi-3-Mini-128K-Instruct, quantized for fast, scalable inference on CPUs, GPUs, and mobile devices, supporting long-context AI applications.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads1
  • Views121
  • File Size0

Phi-3-Medium-4K-Instruct ONNX-DirectML - Optimized AI Model for Windows GPU Inference
An ONNX-optimized version of Phi-3-Medium-4K-Instruct, designed for efficient AI inference on Windows machines using DirectML, supporting INT4 quantization for high-performance execution on AMD, Intel, and NVIDIA GPUs.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads0
  • Views211
  • File Size0


Related Models by Organization Related Models by Organization

microsoft/Phi-3-vision-128k-instruct
Phi-3-vision-128k-instruct is a state-of-the-art multimodal model by Microsoft, designed to process both text and visual inputs with a context length of up to 128,000 tokens.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads12
  • Views283
  • File Size0

Phi-3-Medium-4K-Instruct - Scalable AI Model for Reasoning and Code Generation
A 14B parameter AI model optimized for 4K and 128K token context lengths, designed for advanced reasoning, math, and coding applications, supporting both research and commercial use.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads0
  • Views270
  • File Size0

BiomedBERT - Domain-Specific Biomedical Language Model
A biomedical NLP model pre-trained from scratch on abstracts and full-text articles from PubMed and PubMed Central, achieving state-of-the-art performance on biomedical language understanding tasks.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads102
  • Views1,996
  • File Size0

Phi-3-Medium-128K-Instruct ONNX-CUDA - Optimized AI Model for NVIDIA GPU Inference
An ONNX-optimized version of Phi-3-Medium-128K-Instruct, designed for high-speed, efficient inference on NVIDIA GPUs, supporting FP16 and INT4 quantization for enhanced performance.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads2
  • Views168
  • File Size0

Phi-3-Small-8K-Instruct ONNX-CUDA - Optimized AI Model for NVIDIA GPU Inference
An ONNX-optimized version of Phi-3-Small-8K-Instruct, designed for efficient inference on NVIDIA GPUs, supporting FP16 and INT4 quantization for fast, scalable AI applications.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads1
  • Views174
  • File Size0

Phi-3-Mini-4K-Instruct GGUF - Optimized AI Model for GGUF Inference
A GGUF-optimized version of Phi-3-Mini-4K-Instruct, designed for efficient low-memory AI inference, supporting quantized and full-precision formats for balanced performance and quality.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters1
  • Downloads29
  • Views1,580
  • File Size0

Phi-3-Medium-128K-Instruct - Advanced Long-Context AI for Code and Logical Reasoning
A 14B parameter AI model optimized for 128K token context length, designed for complex reasoning, mathematical problem-solving, and efficient AI applications in commercial and research environments.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads3
  • Views133
  • File Size0

Phi-3-Medium-128K-Instruct ONNX-CPU - Optimized AI Model for CPU Inference
An ONNX-optimized version of Phi-3-Medium-128K-Instruct, designed for efficient long-context inference on CPUs, supporting structured reasoning, text generation, and code processing.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads2
  • Views212
  • File Size0

Phi-3-Mini-128K-Instruct ONNX - Optimized AI Model for Long-Context ONNX Inference
An ONNX-optimized version of Phi-3-Mini-128K-Instruct, quantized for fast, scalable inference on CPUs, GPUs, and mobile devices, supporting long-context AI applications.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads1
  • Views121
  • File Size0

Phi-3-Medium-4K-Instruct ONNX-DirectML - Optimized AI Model for Windows GPU Inference
An ONNX-optimized version of Phi-3-Medium-4K-Instruct, designed for efficient AI inference on Windows machines using DirectML, supporting INT4 quantization for high-performance execution on AMD, Intel, and NVIDIA GPUs.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads0
  • Views211
  • File Size0


Related Models by Sector Related Models by Sector

BiomedBERT - Domain-Specific Biomedical Language Model
A biomedical NLP model pre-trained from scratch on abstracts and full-text articles from PubMed and PubMed Central, achieving state-of-the-art performance on biomedical language understanding tasks.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads102
  • Views1,996
  • File Size0

BiomedVLP-CXR-BERT - Domain-Specific BERT for Chest X-ray Reports
A specialized biomedical language model pre-trained on radiology reports from MIMIC-CXR and PubMed, optimized for radiology NLP tasks such as masked language modeling, phrase grounding, and medical text classification.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads16
  • Views419
  • File Size0

RadEdit: A deep learning biomedical vision models to discover failure cases
A latent diffusion model for editing chest X-ray images by adding or removing abnormalities, designed for stress-testing biomedical vision models and evaluating their robustness in clinical AI research.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads15
  • Views340
  • File Size0

BioViL-T - Temporal Vision-Language Model for Radiology
A domain-specific vision-language model designed for analyzing chest X-rays and radiology reports, leveraging temporal multi-modal pre-training for improved biomedical inference, phrase grounding, and image-text alignment.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads22
  • Views1,461
  • File Size0

BiomedVLP-CXR-BERT-Specialized - Domain-Specific Vision-Language Model for Radiology
A specialized biomedical language model trained on chest X-ray reports from MIMIC-CXR and PubMed, optimized for radiology NLP, masked language modeling, and multi-modal contrastive learning with image-text alignment.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads9
  • Views478
  • File Size0

BiomedCLIP-PubMedBERT_256-vit_base_patch16_224: A biomedical vision-language foundation model
A biomedical vision-language foundation model trained on PMC-15M, using PubMedBERT as the text encoder and Vision Transformer as the image encoder, optimized for cross-modal retrieval, classification, and visual question answering in medical AI applications.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads27
  • Views1,724
  • File Size0

RAD-DINO - Vision Transformer for Medical Image Encoding
A vision transformer model trained with self-supervised learning for encoding chest X-rays, optimized for medical image analysis, classification, retrieval, and report generation.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads17
  • Views1,174
  • File Size0

RAD-DINO-MAIRA-2 - Vision Transformer for Medical Imaging
A vision transformer model trained for chest X-ray encoding using self-supervised learning, optimized for medical image analysis and report generation.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads14
  • Views1,019
  • File Size0

MANAS-1-small-40M
A state-of-the-art EEG Brain Foundation Model.
MANNAS AI (INTELLIHEALTH WORLD PVT. LTD.)
  • See Upvoters0
  • Downloads5
  • Views164
  • File Size1.65 GB

Parrotlet-A-2p5-Pro
Medical ASR model for Indian English, Hindi, Telugu, Kannada, Marathi.
EKA CARE
  • See Upvoters0
  • Downloads5
  • Views216
  • File Size0


Related Models by Task Type Related Models by Task Type

RAG Engine
Python script that implements a Retrieval‑Augmented Generation (RAG) pipeline for document question answering.
Text Generation
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views23
  • File Size0

CoRover-BharatGPT-Instruct
BharatGPT-Instruct E2B is a multilingual language model by CoRover.ai, designed to deliver high-quality, culturally relevant AI responses across Indian languages.
COROVER PRIVATE LIMITED
  • See Upvoters0
  • Downloads0
  • Views62
  • File Size9.57 GB

CoRover-BharatGPT-mini
BharatGPT Mini - A compact, Transformer-based language model developed by CoRover, pretrained on large-scale text data to understand and generate natural language, advancing India’s indigenous AI capabilities.
COROVER PRIVATE LIMITED
  • See Upvoters0
  • Downloads0
  • Views138
  • File Size967.26 MB

CoRover-BharatGPT-3B-Indic
A multilingual model fine-tuned on authentic conversational data across Indic languages, supporting translation, summarisation, and text generation. Ideal for Secure RAG (S-RAG) and domain-specific fine-tuning, it enables the development of sovereign, multilingual AI agents, chatbots, voicebots, and virtual assistants.
COROVER PRIVATE LIMITED
  • See Upvoters0
  • Downloads0
  • Views23
  • File Size6 GB

Kaveri-4B
Kaveri-4B is a multilingual text-generation model for conversational AI, instruction following, reasoning, coding assistance, summarization, translation, and general-purpose NLP tasks.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views48
  • File Size7.51 GB

Kaveri-1-5B
Kaveri-1.5B is a lightweight multilingual text-generation assistant by RiyaVibe for general chat, instruction following, basic question answering, simple coding help, basic math, translation, and local or cloud inference.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views34
  • File Size2.89 GB

Kaveri-05b
Kaveri 0.5B is a lightweight multilingual conversational AI assistant designed for local inference, instruction following, chat, and agent workflows.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views58
  • File Size739.29 MB

gnani-evon-v3-30B-A3B
Hybrid Mamba2–Transformer MoE, 30B total / ~3.5B active, trained end-to-end for Indic capability across 11 languages. 128K context, tool calling, native-script output. Apache-2.0.
GNANI INNOVATIONS PRIVATE LIMITED
  • See Upvoters0
  • Downloads4
  • Views203
  • File Size0

Phi-1.5 - Lightweight Transformer Model for Text Generation and Coding
A 1.3B parameter Transformer model trained on structured QA, NLP tasks, and Python code, optimized for text generation, summarization, and creative writing, with no fine-tuning from human feedback.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters0
  • Downloads43
  • Views1,706
  • File Size0

Phi-3-Mini-4K-Instruct - Lightweight AI Model for Reasoning and Efficient AI Applications
A 3.8B parameter AI model optimized for memory-efficient reasoning, instruction following, and long-context processing, designed for compute-constrained environments and latency-sensitive applications.
MICROSOFT CORPORATION (INDIA) PVT. LTD.
  • See Upvoters1
  • Downloads23
  • Views388
  • File Size0