mozay22/Discharge-summary-Fine-Tune

该数据集提供了为细调大型语言模型（LLM）而设计的合成出院摘要，这些任务专注于从患者记录中提取医疗和人口统计信息。它帮助模型学会识别并将实体如患者姓名、年龄、诊断、药物和手术等信息结构化成字典格式。

This dataset provides synthetic discharge summaries designed for fine-tuning large language models (LLMs) on named entity recognition (NER) tasks focused on extracting medical and demographic information from patient records. It helps models learn to identify and structure entities like patient names, ages, diagnoses, medications, and procedures into a dictionary format.