remvoing cuda dependencies

app.py

@@ -81,7 +81,9 @@ def generate(
 def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
     generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 1, 0.95, 50)
     for x in generator:
+        print(f"Printing x before pass {x}")
         pass
+    print(f"Printing x after pass {x}")
     return '', x
 
 

model.py

@@ -28,6 +28,7 @@ if not torch.cuda.is_available():
         device_map='auto',
         use_auth_token=True
     )
+    print("Loaded the model!")
 else:
     model = None
 tokenizer = AutoTokenizer.from_pretrained(model_id)
@@ -61,7 +62,7 @@ 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.,