Update app.py

app.py

@@ -50,6 +50,13 @@ def llm_response(history,text,img):
 def sentence_builder(animal, place):
     return f"""how many {animal}s from the {place} are shown in the picture?"""
 
+descript1 = gr.Markdown("""
+    ## Multimodal Descript ##
+    
+    <h5 align="center"><i>"Imagine learning XXXX."</i></h5>
+    
+    Multimodal-CoT incorporates vision features in a decoupled training framework. The framework consists of two training stages: (i) rationale generation and (ii) answer inference. Both stages share the same model architecture but differ in the input and output.
+    """)
 # gradio block
     
 with gr.Blocks(theme='snehilsanyal/scikit-learn') as app1:
@@ -83,6 +90,7 @@ with gr.Blocks(theme='snehilsanyal/scikit-learn') as app1:
 
 with gr.Blocks(theme='snehilsanyal/scikit-learn') as app2:
     gr.Markdown("## MM 2 ##")
+    description = descript1
     with gr.Row():
         image_box = gr.Image(type="filepath")