Update app.py

app.py

@@ -89,93 +89,94 @@ with gr.Blocks(fill_height=True) as demo:
         output = gr.Textbox(label="Output")
         
     with gr.Accordion(label="Example Inputs and Advanced Generation Parameters"):
-      examples=[["./example_images/docvqa_example.png", "How many items are sold?", "Greedy", 0.4, 512, 1.2, 0.8],
+        examples=[["./example_images/docvqa_example.png", "How many items are sold?", "Greedy", 0.4, 512, 1.2, 0.8],
                     ["./example_images/s2w_example.png", "What is this UI about?", "Greedy", 0.4, 512, 1.2, 0.8],
                     ["./example_images/example_images_travel_tips.jpg", "I want to go somewhere similar to the one in the photo. Give me destinations and travel tips.",  0.4, 512, 1.2, 0.8],
                     ["./example_images/chicken_on_money.png", "Can you tell me a very short story based on this image?", 0.4, 512, 1.2, 0.8],
                     ["./example_images/baklava.png", "Where is this pastry from?", 0.4, 512, 1.2, 0.8],
                     ["./example_images/dummy_pdf.png", "How much percent is the order status?", 0.4, 512, 1.2, 0.8],
                     ["./example_images/art_critic.png", "As an art critic AI assistant, could you describe this painting in details and make a thorough critic?.", 0.4, 512, 1.2, 0.8]]
-      gr.Examples(
-                    examples = examples,
-                    inputs=[image_input, query_input, decoding_strategy, temperature, 
-                                                          max_new_tokens, repetition_penalty, top_p],
-                    outputs=output,
-                    fn=model_inference
-                )
-      # Hyper-parameters for generation
-      max_new_tokens = gr.Slider(
-          minimum=8,
-          maximum=1024,
-          value=512,
-          step=1,
-          interactive=True,
-          label="Maximum number of new tokens to generate",
-      )
-      repetition_penalty = gr.Slider(
-          minimum=0.01,
-          maximum=5.0,
-          value=1.2,
-          step=0.01,
-          interactive=True,
-          label="Repetition penalty",
-          info="1.0 is equivalent to no penalty",
-      )
-      temperature = gr.Slider(
-          minimum=0.0,
-          maximum=5.0,
-          value=0.4,
-          step=0.1,
-          interactive=True,
-          label="Sampling temperature",
-          info="Higher values will produce more diverse outputs.",
-      )
-      top_p = gr.Slider(
-          minimum=0.01,
-          maximum=0.99,
-          value=0.8,
-          step=0.01,
-          interactive=True,
-          label="Top P",
-          info="Higher values is equivalent to sampling more low-probability tokens.",
-      )
-      decoding_strategy = gr.Radio(
-          [
-              "Greedy",
-              "Top P Sampling",
-          ],
-          value="Greedy",
-          label="Decoding strategy",
-          interactive=True,
-          info="Higher values is equivalent to sampling more low-probability tokens.",
-      )
-      decoding_strategy.change(
-          fn=lambda selection: gr.Slider(
-              visible=(
-                  selection in ["contrastive_sampling", "beam_sampling", "Top P Sampling", "sampling_top_k"]
-              )
-          ),
-          inputs=decoding_strategy,
-          outputs=temperature,
-      )
-
-      decoding_strategy.change(
-          fn=lambda selection: gr.Slider(
-              visible=(
-                  selection in ["contrastive_sampling", "beam_sampling", "Top P Sampling", "sampling_top_k"]
-              )
-          ),
-          inputs=decoding_strategy,
-          outputs=repetition_penalty,
-      )
-      decoding_strategy.change(
-          fn=lambda selection: gr.Slider(visible=(selection in ["Top P Sampling"])),
-          inputs=decoding_strategy,
-          outputs=top_p,
-      )
-      
-    submit_btn.click(model_inference, inputs = [image_input, query_input, decoding_strategy, temperature, 
-                                                  max_new_tokens, repetition_penalty, top_p], outputs=output)
-  
+        
+        # Hyper-parameters for generation
+        max_new_tokens = gr.Slider(
+              minimum=8,
+              maximum=1024,
+              value=512,
+              step=1,
+              interactive=True,
+              label="Maximum number of new tokens to generate",
+          )
+        repetition_penalty = gr.Slider(
+              minimum=0.01,
+              maximum=5.0,
+              value=1.2,
+              step=0.01,
+              interactive=True,
+              label="Repetition penalty",
+              info="1.0 is equivalent to no penalty",
+          )
+        temperature = gr.Slider(
+              minimum=0.0,
+              maximum=5.0,
+              value=0.4,
+              step=0.1,
+              interactive=True,
+              label="Sampling temperature",
+              info="Higher values will produce more diverse outputs.",
+          )
+        top_p = gr.Slider(
+              minimum=0.01,
+              maximum=0.99,
+              value=0.8,
+              step=0.01,
+              interactive=True,
+              label="Top P",
+              info="Higher values is equivalent to sampling more low-probability tokens.",
+          )
+        decoding_strategy = gr.Radio(
+              [
+                  "Greedy",
+                  "Top P Sampling",
+              ],
+              value="Greedy",
+              label="Decoding strategy",
+              interactive=True,
+              info="Higher values is equivalent to sampling more low-probability tokens.",
+          )
+        decoding_strategy.change(
+              fn=lambda selection: gr.Slider(
+                  visible=(
+                      selection in ["contrastive_sampling", "beam_sampling", "Top P Sampling", "sampling_top_k"]
+                  )
+              ),
+              inputs=decoding_strategy,
+              outputs=temperature,
+          )
+        
+        decoding_strategy.change(
+              fn=lambda selection: gr.Slider(
+                  visible=(
+                      selection in ["contrastive_sampling", "beam_sampling", "Top P Sampling", "sampling_top_k"]
+                  )
+              ),
+              inputs=decoding_strategy,
+              outputs=repetition_penalty,
+          )
+        decoding_strategy.change(
+              fn=lambda selection: gr.Slider(visible=(selection in ["Top P Sampling"])),
+              inputs=decoding_strategy,
+              outputs=top_p,
+          )
+        gr.Examples(
+                        examples = examples,
+                        inputs=[image_input, query_input, decoding_strategy, temperature, 
+                                                              max_new_tokens, repetition_penalty, top_p],
+                        outputs=output,
+                        fn=model_inference
+                    )
+          
+        submit_btn.click(model_inference, inputs = [image_input, query_input, decoding_strategy, temperature, 
+                                                      max_new_tokens, repetition_penalty, top_p], outputs=output)
+
 
 demo.launch(debug=True)