Update app.py

app.py

@@ -27,8 +27,8 @@ def chat(message, history):
     add_generation_prompt=True
     )   
 
-    model_inputs = tokenizer([text], return_tensors="pt").to("cuda")
-    # model_inputs = tokenizer([text], return_tensors="pt")
+    # model_inputs = tokenizer([text], return_tensors="pt").to("cuda")
+    model_inputs = tokenizer([text], return_tensors="pt")
     streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,