Kerassy/Qwen3.5-9B-Medical-Reasoning
Kerassy/Qwen3.5-9B-Medical-Reasoning is a 9-billion parameter model, fine-tuned from Qwen/Qwen3.5-9B, specifically optimized for complex clinical reasoning and medical question-answering. It leverages chain-of-thought (CoT) fine-tuning to generate explicit step-by-step diagnostic reasoning within tags. This model is designed for medical research and evaluation of CoT capabilities in compact LLMs, offering both detailed reasoning and direct answer modes.
Loading preview...
Kerassy/Qwen3.5-9B-Medical-Reasoning: Medical Reasoning with Chain-of-Thought
Kerassy/Qwen3.5-9B-Medical-Reasoning is a 9-billion parameter model, fine-tuned from the Qwen3.5-9B base, specifically engineered for advanced medical reasoning. Its core differentiator is the integration of chain-of-thought (CoT) fine-tuning on medical reasoning datasets, enabling it to produce explicit, step-by-step diagnostic thought processes within <think> tags before delivering a final medical conclusion.
Key Capabilities
- Explainable Medical Reasoning: Generates detailed CoT traces, enhancing transparency and preventing superficial responses in complex clinical scenarios.
- Dual Output Modes: Supports a default "Thinking Mode" for detailed reasoning and a "Direct Mode" for succinct answers by pre-filling empty
<think>tags. - Strong Medical Performance: Aims to outperform standard base models and many 7B-13B non-reasoning models on board-style medical examinations, though specific evaluation results are pending.
- Efficient Fine-Tuning: Developed using Unsloth for LoRA fine-tuning on a single NVIDIA A100 GPU, utilizing the
FreedomIntelligence/medical-o1-reasoning-SFTdataset.
Good For
- Medical Research: Ideal for evaluating chain-of-thought capabilities in smaller language models within a medical context.
- AI-Assisted Clinical Reasoning Analysis: Useful for benchmarking and analyzing AI's ability to simulate clinical diagnostic processes.
Important Note: This model is for research and evaluation only and should not be used for direct patient care or clinical decision-making.