Update app.py

app.py

@@ -18,7 +18,7 @@ model = AutoModelForCausalLM.from_pretrained(model_name)
 def ask_medical_question(question):
     prompt = f"<|start_header_id|>system<|end_header_id|> You are a Medical AI chatbot assistant. <|eot_id|><|start_header_id|>User: <|end_header_id|>This is the question: {question}<|eot_id|>"
 
-    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
     outputs = model.generate(
         **inputs,
         max_new_tokens=256,