from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-3B-Thinking",
    torch_dtype="auto",
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "xingqiang/Medical-NER-Qwen-4B-Thinking-plus")
tokenizer = AutoTokenizer.from_pretrained("xingqiang/Medical-NER-Qwen-4B-Thinking-plus")

# Generate medical analysis
text = "Hepatitis C virus causes chronic liver infection."
messages = [
    {"role": "user", "content": f"Extract medical entities and relationships from: {text}"}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)