Update app.py

app.py

@@ -18,7 +18,6 @@ model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_c
 
 @spaces.GPU
 def generate_response(user_input, max_new_tokens, temperature):
-    # Format message with the command-r chat template
     messages = [{"role": "user", "content": user_input}]
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
 
@@ -49,18 +48,23 @@ def setup_examples():
 with gr.Blocks() as demo:
     gr.Markdown(title)
     with gr.Row():
-        message_box = gr.Textbox(lines=2, label="Your Message")
         max_new_tokens_slider = gr.Slider(minimum=10, maximum=100, value=50, label="Max New Tokens")
         temperature_slider = gr.Slider(minimum=0.1, maximum=1.0, step=0.1, value=0.3, label="Temperature")
+    message_box = gr.Textbox(lines=2, label="Your Message")
     generate_button = gr.Button("Try🫡Command-R")
     output_box = gr.Textbox(label="🫡Command-R")
-    
+    with gr.Accordion("🫡Examples", open=False):
+        gr.Examples(
+            examples=examples,
+            inputs=[message_box, max_new_tokens_slider, temperature_slider],
+            outputs=output_box,
+            fn=generate_response,
+            cache_examples=True
+        )
+
     generate_button.click(
         fn=generate_response,
         inputs=[message_box, max_new_tokens_slider, temperature_slider],
         outputs=output_box
     )
-    setup_examples_button = gr.Button("Load Example")
-    setup_examples_button.click(fn=setup_examples, inputs=[], outputs=[])
-
-demo.launch()
+demo.launch()