Agnania/EviNurse-32B
Agnania/EviNurse-32B is a 32.8 billion parameter domain-specific large language model, based on Qwen3-32B, developed for evidence-based nursing. It is fine-tuned for nursing-domain question answering and evaluated through automated multiple-choice testing and expert assessment. This model supports research in nursing AI and evidence-based nursing, offering a specialized tool for healthcare-related language tasks.
Loading preview...
EviNurse-32B: A Specialized LLM for Evidence-Based Nursing
EviNurse-32B is a 32.8 billion parameter large language model, built upon the Qwen3-32B architecture, specifically fine-tuned for evidence-based nursing applications. Developed by Agnania, this model underwent supervised fine-tuning to excel in nursing-domain question answering and related use cases.
Key Capabilities & Features
- Domain-Specific Expertise: Adapted for evidence-based nursing, providing specialized knowledge beyond general-purpose LLMs.
- Robust Evaluation: Assessed through automated multiple-choice tests (using the NursData-MCQ benchmark), expert review of short-answer responses, and real-world usability studies with nurses.
- Research-Oriented: Released to support reproducible research in nursing AI, offering a model artifact for comparative evaluations.
- Qwen3-32B Base: Leverages the strong foundation of the Qwen3-32B model, with a context length of 40,960 tokens.
Intended Use Cases
EviNurse-32B is primarily intended for research purposes, including:
- Developing and evaluating nursing-domain language models.
- Enhancing evidence-based nursing question answering systems.
- Exploring retrieval-augmented generation (RAG) for nursing evidence.
- Automated benchmarking using the NursData-MCQ dataset.
- Comparative studies between general-purpose and domain-specific LLMs in healthcare.
Important Note: This model is not a medical device and should not be used as a substitute for professional clinical judgment.