大模型的实践应用1-基于BERT模型训练医疗智能诊断问答的运用研究，协助医生进行疾病诊断

    "question","answer"
    "高血压的症状有哪些？","高血压的症状可能包括：头痛、眩晕、心悸等。"
    "糖尿病应该如何饮食？","糖尿病患者应该吃低糖、高纤维的食物，避免吃高糖、高油脂的食物。"
    "什么是冠心病？","冠心病是由于冠状动脉供血不足引起的心肌缺血性疾病。"
    "怎样预防感冒？","预防感冒的方法包括勤洗手、保持室内通风、避免接触已经感染的人等。"
    "什么是肺癌？","肺癌是一种恶性肿瘤，起源于肺部组织的恶性肿瘤。"
    "如何预防肥胖？","预防肥胖的方法包括均衡饮食、适量运动、避免过度进食等。"
    "什么是骨质疏松？","骨质疏松是骨骼中骨量减少、骨质变薄、骨密度降低的一种疾病。"
    "中风有哪些症状？","中风的症状可能包括突然出现的面部下垂、言语困难、肢体无力等。"
    "如何预防心脏病？","预防心脏病的方法包括保持良好的饮食习惯、适量运动、避免吸烟等。"
    "什么是抑郁症？","抑郁症是一种常见的精神障碍，患者表现出持续的沮丧情绪和对生活失去兴趣。"
    "如何保护眼睛健康？","保护眼睛健康的方法包括合理用眼、定期休息、远离电子屏幕等。"
    "什么是贫血？","贫血是指人体血液中红细胞数量或质量不足导致供氧能力下降的状况。"

    import torch
    from torch.utils.data import Dataset, DataLoader
    from transformers import AutoTokenizer, AutoModelForQuestionAnswering, AdamW
    
    # 使用预训练的模型和分词器
    model_name = "bert-base-uncased"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForQuestionAnswering.from_pretrained(model_name)
    
    # 医疗问答数据集
    class MedicalQADataset(Dataset):
    def __init__(self, file_path, tokenizer):
        self.tokenizer = tokenizer
        self.questions = []
        self.answers = []
        with open(file_path, 'r', encoding='utf-8') as f:
            next(f)  # 忽略csv文件的表头
            for line in f:
                question, answer = line.strip().split(',')
                self.questions.append(question)
                self.answers.append(answer)
    
    def __len__(self):
        return len(self.questions)
    
    def __getitem__(self, idx):
        question, answer = self.questions[idx], self.answers[idx]
        encodings = self.tokenizer.encode_plus(question, answer, truncation=True, padding='max_length', max_length=128)
        item = {key: torch.tensor(val) for key, val in encodings.items()}
        item['labels'] = item['input_ids']
        return item
    
    # 创建数据加载器
    dataset = MedicalQADataset('medical_qa.csv', tokenizer)
    dataloader = DataLoader(dataset, batch_size=32, shuffle=True)
    
    # 训练模型
    device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
    model.to(device)
    optimizer = AdamW(model.parameters(), lr=1e-5)
    
    for epoch in range(3):
    total_loss = 0
    for batch in dataloader:
        input_ids = batch['input_ids'].to(device)
        attention_mask = batch['attention_mask'].to(device)
        labels = batch['labels'].to(device)
        outputs = model(input_ids, attention_mask=attention_mask, labels=labels)
        loss = outputs[0]
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()
        total_loss += loss.item()
    print(f"Epoch {epoch+1}: {total_loss}")

    def get_answer(question):
    inputs = tokenizer(question, return_tensors='pt')
    inputs = {k: v.to(device) for k, v in inputs.items()}
    outputs = model(**inputs)
    answer_start_scores, answer_end_scores = outputs.start_logits, outputs.end_logits
    answer_start = torch.argmax(answer_start_scores)
    answer_end = torch.argmax(answer_end_scores) + 1
    answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs['input_ids'][0][answer_start:answer_end]))
    return answer