Update app.py

app.py

@@ -25,7 +25,7 @@ def predict(message, history, temperature, max_tokens, top_p, top_k):
     stop = StopOnTokens()
     messages = "".join(["".join(["\n<|end|>\n<|user|>\n"+item[0], "\n<|end|>\n<|assistant|>\n"+item[1]]) for item in history_transformer_format])
     model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
-    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=300., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,
         streamer=streamer,
@@ -50,7 +50,8 @@ demo = gr.ChatInterface(
     additional_inputs=[
         gr.Slider(0.1, 0.9, value=0.7, label="Temperature"),
         gr.Slider(512, 8192, value=4096, label="Max Tokens"),
-        gr.Slider(0.1, 0.9, value=0.7, label="top_p"),
+        gr.Slider(0.1, 0.9, value=0.7, label="top_p"
+),
         gr.Slider(10, 90, value=40, label="top_k"),
     ]
 )