Update app.py

app.py

@@ -95,10 +95,10 @@ def hanuman_flash_stream(message, history):
     generate_kwargs = dict(
         **model_inputs,
         streamer=streamer,
-        max_new_tokens=4096,
+        max_new_tokens=512,
         use_cache=True,
         do_sample=True,
-        temperature=0.7,
+        temperature=1,
         top_p=0.90
     )