Update app.py

app.py

@@ -28,24 +28,12 @@ def predict(message, history):
     history_transformer_format = history + [[message, ""]]
     stop = StopOnTokens()
 
-    '''
-    inputs = tokenizer(
-    [
-        alpaca_prompt.format(
-            message, # instruction
-            "", # input
-            "", # output - leave this blank for generation!
-        )
-    ], return_tensors = "pt").to("cuda")
-
-    text_streamer = TextStreamer(tokenizer)
-    _ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 2048)
-    '''
 
     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,
@@ -67,6 +55,4 @@ def predict(message, history):
             partial_message += new_token
             yield partial_message
 
-gr.ChatInterface(predict).launch(debug=True)
-
-gr.close_all()
+gr.ChatInterface(predict).launch(debug=True)