### Question:
First-line treatment for hypertensive emergency?

### Options:
A) Oral amlodipine
B) IV labetalol or IV nitroprusside
C) Sublingual nifedipine
D) IM hydralazine

### Answer:

B) IV labetalol or IV nitroprusside

Explanation:
Hypertensive emergencies require immediate IV therapy.
Labetalol is a combined alpha and beta blocker that rapidly
reduces blood pressure safely. Nitroprusside is a vasodilator
used when faster or more precise control is needed.

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

BASE_MODEL   = "Qwen/Qwen3-1.7B"
ADAPTER_REPO = "HK2184/medqa-qwen3-lora"

tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True)
tokenizer.pad_token    = tokenizer.eos_token
tokenizer.padding_side = "left"

base = AutoModelForCausalLM.from_pretrained(
    BASE_MODEL,
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

model = PeftModel.from_pretrained(base, ADAPTER_REPO)
model = model.merge_and_unload()
model.eval()

prompt = """### Question:
First-line treatment for hypertensive emergency?

### Options:
A) Oral amlodipine
B) IV labetalol or IV nitroprusside
C) Sublingual nifedipine
D) IM hydralazine

### Answer:
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    out = model.generate(
        **inputs,
        max_new_tokens=200,
        do_sample=True,
        temperature=0.7,
        top_p=0.9,
        repetition_penalty=1.3,
        pad_token_id=tokenizer.eos_token_id,
    )
new = out[0][inputs["input_ids"].shape[-1]:]
print(tokenizer.decode(new, skip_special_tokens=True))