Update app.py

app.py

@@ -39,6 +39,7 @@ def respond(
     outputs = pipeline(
         messages,
         max_new_tokens=max_tokens,
+        do_sample = True,
         temperature=temperature,
         top_p=top_p,
         eos_token_id=terminators
@@ -56,7 +57,7 @@ with gr.Blocks() as demo:
         respond,
         additional_inputs=[
             gr.Slider(minimum=1, maximum=2048, value=256, step=1, label="Max new tokens"),
-            gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+            gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.1, label="Temperature"),
             gr.Slider(
                 minimum=0.1,
                 maximum=1.0,