EpistemeAI/Reasoning-Medical0.1-27B
EpistemeAI/Reasoning-Medical0.1-27B is a 27 billion parameter causal language model developed by EpistemeAI, fine-tuned for advanced medical reasoning. It excels in professional medicine, medical genetics, college biology/medicine, and clinical knowledge, incorporating Chain-of-Thought reasoning. The model features a native context length of 262,144 tokens, extensible up to 1,010,000 tokens, and includes a vision encoder, making it suitable for complex medical question-answering and reasoning tasks.
Loading preview...
EpistemeAI/Reasoning-Medical0.1-27B: Advanced Medical Reasoning Model
EpistemeAI/Reasoning-Medical0.1-27B is a 27 billion parameter causal language model developed by EpistemeAI, specifically fine-tuned for advanced medical reasoning. This model integrates Chain-of-Thought reasoning to enhance its ability to answer complex medical questions step-by-step. It was trained on a large-scale dataset of 100,000 records, curated from various public medical reasoning datasets, and optimized using the Unsloth method for efficient fine-tuning.
Key Capabilities
- Specialized Medical Reasoning: Designed for professional medicine, medical genetics, college biology/medicine, and clinical knowledge.
- Extended Context Window: Natively supports 262,144 tokens, extensible up to 1,010,000 tokens using YaRN scaling.
- Multimodal Input: Capable of processing text, image, and video inputs, making it versatile for diverse medical data.
- High Performance: Achieves strong benchmark results, including 0.93 on MMLU-Pro Biology, 0.968 on MMLU-ProX Biology, and 0.969 on MedQA, outperforming other medical models like MedGemma 1 27B.
- Agentic Usage: Excels in tool-calling capabilities, recommended for use with Qwen-Agent for building agent applications.
Good For
- Medical Education Applications: Assisting in learning and understanding complex medical concepts.
- Research Copilots: Supporting researchers in biotech and pharma with literature analysis and reasoning.
- Private Medical Reasoning Deployments: For secure and specialized medical question-answering.
- Model Benchmarking and Safety Evaluation: Providing a robust model for evaluating medical AI systems.
Safety Notice: This model is strictly for benign medical and scientific reasoning. It must not be used for any harmful activities, including biological or chemical weapon development, and all outputs require expert review and compliance with safety standards.