Update app.py

app.py

@@ -17,7 +17,7 @@ def load_llama_model():
     print("Loading base model...")
     model = AutoModelForCausalLM.from_pretrained(
         BASE_MODEL,
-        torch_dtype=torch.float32 
+        torch_dtype=torch.float32,
         device_map="cpu",  # Ensure it runs on CPU
         token=HUGGINGFACE_TOKEN
     )