resetting it to use CPU

app.py

@@ -30,9 +30,10 @@ As a derivate work of [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama
 this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/USE_POLICY.md).
 """
 
+'''
 if not torch.cuda.is_available():
     DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'
-
+'''
 
 def clear_and_save_textbox(message: str) -> tuple[str, str]:
     return '', message

model.py

@@ -8,7 +8,7 @@ from huggingface_hub import login
 
 model_id = 'jaymojnidar/Llama-2-7b-chat-hf-sharded-bf16-5GBMAX'
 
-if torch.cuda.is_available():
+if not torch.cuda.is_available():
     tok = os.environ['HF_TOKEN']
     login(new_session=True,
           write_permission=False,
@@ -61,7 +61,7 @@ def run(message: str,
         top_p: float = 0.95,
         top_k: int = 50) -> Iterator[str]:
     prompt = get_prompt(message, chat_history, system_prompt)
-    inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to('cuda')
+    inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to(torch.device) #.to('cuda')
 
     streamer = TextIteratorStreamer(tokenizer,
                                     timeout=10.,