Update app.py

app.py

@@ -32,8 +32,7 @@ def predict(message, history):
     messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])
                 for item in history_transformer_format])
 
-    model_inputs = tokenizer([messages], return_tensors="pt")
-    #.to("cuda")
+    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,