Update app.py

app.py

@@ -50,7 +50,6 @@ def run_generation(user_text, use_assistant, temperature, max_new_tokens):
     for new_text in streamer:
         model_output += new_text
         yield [model_output, round(time.time() - start, 3)]
-    # return [model_output, round(time.time() - start, 3)]
 
 
 def reset_textbox():
@@ -81,7 +80,7 @@ with gr.Blocks() as demo:
                 minimum=1, maximum=500, value=100, step=1, interactive=True, label="Max New Tokens",
             )
             temperature = gr.Slider(
-                minimum=0.0, maximum=2.0, value=0.0, step=0.1, interactive=True, label="Temperature (0.0 = Greedy)",
+                minimum=0.0, maximum=2.0, value=0.6, step=0.05, interactive=True, label="Temperature (0.0 = Greedy)",
             )
             gr.Markdown("### Generation time (seconds)")
             generation_time = gr.Textbox(lines=1, interactive=False, show_label=False)