Update app.py

app.py

@@ -101,80 +101,80 @@ with gr.Blocks(fill_height=True) as demo:
                     outputs=output,
                     fn=model_inference
                 )
-        with gr.Accordion():
-          # 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)
+    with gr.Accordion():
+      # 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)
+  
 
 demo.launch(debug=True)