first version

app.py

@@ -33,14 +33,14 @@ 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
+@spaces.GPU
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],