Update app.py

app.py

@@ -29,16 +29,16 @@ As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-
 this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
 """
 
-'''if not torch.cuda.is_available():
+if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
-'''
 
-'''if torch.cuda.is_available():'''
-model_id = "meta-llama/Llama-2-7b-chat-hf"
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-tokenizer.use_default_system_prompt = False
 
+if torch.cuda.is_available():
+    model_id = "meta-llama/Llama-2-7b-chat-hf"
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    tokenizer.use_default_system_prompt = False
+    
 
 @spaces.GPU
 def generate(