unsloth-fine-tuning-framework-with-LoRA-and-CoT-Q-A-data-set-wandb-visual-training.DeepSeek-R1-Distill-Qwen-1.5B for medical diagnosis and clinical reasoning tasks. The project focuses on Chain-of-Thought (CoT) supervised fine-tuning, enabling the model to generate transparent, step-by-step medical reasoning.