medicalai/ClinicalGPT-R1-Qwen-7B-EN-preview

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 31, 2025License:afl-3.0Architecture:Transformer0.0K Warm

ClinicalGPT-R1-Qwen-7B-EN-preview is a 7.6 billion parameter medical language model developed by medicalai, based on the Qwen architecture. This model is specifically designed and optimized for disease diagnosis assistance, providing detailed and comprehensive diagnostic analyses from medical records. It excels in processing clinical text to generate diagnostic results, making it suitable for specialized medical AI applications.

Loading preview...

ClinicalGPT-R1-Qwen-7B-EN-preview Overview

ClinicalGPT-R1-Qwen-7B-EN-preview is a specialized 7.6 billion parameter language model built upon the Qwen architecture, developed by medicalai. Its primary focus is on medical applications, particularly in assisting with disease diagnosis.

Key Capabilities

  • Detailed Diagnostic Analysis: The model is engineered to process medical records and provide comprehensive diagnostic analyses.
  • Medical Text Understanding: It demonstrates proficiency in interpreting clinical context to derive diagnostic results.
  • Specialized Medical AI: Optimized for tasks within the medical domain, distinguishing it from general-purpose LLMs.

Good For

  • Disease Diagnosis Assistance: Ideal for applications requiring automated or semi-automated diagnostic support based on patient data.
  • Medical Record Analysis: Useful for extracting and synthesizing information from clinical notes to aid in diagnosis.
  • Research in Medical AI: Provides a strong foundation for further development and research in medical language processing.

For more technical details and to explore the codebase, refer to the GitHub repository. If you utilize this model in your work, please consider citing the associated publication: Wang, G., Liu, X., Liu, H., Yang, G. et al. A Generalist Medical Language Model for Disease Diagnosis Assistance. Nat Med (2025). https://doi.org/10.1038/s41591-024-03416-6.