modify model load

app.py

@@ -41,12 +41,24 @@ def load_model():
     try:
         tokenizer = AutoTokenizer.from_pretrained(model_name, token=access_token, clean_up_tokenization_spaces=False)
         model = AutoModelForCausalLM.from_pretrained(model_name, token=access_token)
-        device = 0 if torch.cuda.is_available() else -1
+        
+        # 디버깅: GPU/CPU 확인 및 출력
+        if torch.cuda.is_available():
+            print("Using GPU")
+            device = 0
+        else:
+            print("Using CPU")
+            device = -1
+        
+        # 디버깅: device 출력
+        print(f"Device: {device}")
+
         return pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=150, temperature=0.1, device=device)
     except Exception as e:
         print(f"Error loading model: {e}")
         return None
 
+
 # 페이지 UI
 def main():
     st.title("Welcome to GemmaPaperQA")