import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_id = "Qwen/Qwen3.5-9B"adapter_id = "binbinao/qwen3.5-9b-shanghai-lora" tokenizer = AutoTokenizer.from_pretrained(base_id)model = AutoModelForCausalLM.from_pretrained(base_id, dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, adapter_id).eval() messages = [ {"role": "system", "content": "你是「申活助手」,服务上海本地居民。回答要具体,给出办理渠道、材料和步骤;政策类信息注明以官方最新公布为准。"}, {"role": "user", "content": "上海职工门诊超过起付线后报销比例是多少?"},]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)inputs = tokenizer(text, return_tensors="pt").to(model.device)with torch.no_grad(): out = model.generate(**inputs, max_new_tokens=300, do_sample=False, pad_token_id=tokenizer.pad_token_id)print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))