min width

app.py

@@ -69,7 +69,15 @@ with gr.Blocks() as demo:
     )
 
     with gr.Row():
-        with gr.Column():
+        with gr.Column(scale=4):
+            user_text = gr.Textbox(
+                placeholder="A sequence: one, two, three, ",
+                label="Prompt"
+            )
+            model_output = gr.Textbox(label="Model output", lines=10, interactive=False)
+            button_submit = gr.Button(value="Submit")
+
+        with gr.Column(scale=1, min_width=200):
             gr.Markdown("### Generation Settings")
             use_assistant = gr.Checkbox(label="Use Assisted Generation", value=True)
             max_new_tokens = gr.Slider(
@@ -78,17 +86,9 @@ with gr.Blocks() as demo:
             temperature = gr.Slider(
                 minimum=0.0, maximum=2.0, value=0.0, step=0.1, interactive=True, label="Temperature (0.0 = Greedy)",
             )
-        with gr.Column():
             gr.Markdown("### Generation time (seconds)")
             generation_time = gr.Textbox(lines=1, interactive=False, show_label=False)
 
-    user_text = gr.Textbox(
-        placeholder="A sequence: one, two, three, ",
-        label="Prompt"
-    )
-    model_output = gr.Textbox(label="Model output", lines=10, interactive=False)
-    button_submit = gr.Button(value="Submit")
-
     generate_inputs = [user_text, use_assistant, temperature, max_new_tokens]
     generate_outputs = [model_output, generation_time]
     user_text.submit(run_generation, generate_inputs, generate_outputs)