Update app.py

app.py

@@ -30,7 +30,7 @@ def predict(message, history):
     # Formatting the input for the model.
     messages = "</s>".join(["</s>".join(["\n<|user|>" + item[0], "\n<|assistant|>" + item[1]])
                         for item in history_transformer_format])
-    model_inputs = tokenizer([messages], return_tensors="pt").to(device)
+    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
     streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,