Update app.py

app.py

@@ -68,13 +68,12 @@ def check_rand(inp,val):
     
 with gr.Blocks() as app:
     gr.HTML("""<center><h1 style='font-size:xx-large;'>Google Gemma Models</h1><br><h3>running on Huggingface Inference Client</h3><br><h7>EXPERIMENTAL""")
+    chat_b = gr.Chatbot(height=500)
     with gr.Group():
-        chat_b = gr.Chatbot(height=500)
         with gr.Row():
             with gr.Column(scale=3):
                 inp = gr.Textbox(label="Prompt")
                 sys_inp = gr.Textbox(label="System Prompt (optional)")
-                client_choice=gr.Dropdown(label="Models",type='index',choices=[c for c in models],value=models[0],interactive=True)
                 with gr.Row():
                     with gr.Column(scale=2):
                         btn = gr.Button("Chat")
@@ -82,9 +81,11 @@ with gr.Blocks() as app:
                         with gr.Group():
                             stop_btn=gr.Button("Stop")
                             clear_btn=gr.Button("Clear")                
+                client_choice=gr.Dropdown(label="Models",type='index',choices=[c for c in models],value=models[0],interactive=True)
+
             with gr.Column(scale=1):
                 with gr.Group():
-                    rand = gr.Checkbox(label="Random", value=True)
+                    rand = gr.Checkbox(label="Random Seed", value=True)
                     seed=gr.Slider(label="Seed", minimum=1, maximum=1111111111111111,step=1, value=rand_val)
                     tokens = gr.Slider(label="Max new tokens",value=6400,minimum=0,maximum=8000,step=64,interactive=True, visible=True,info="The maximum number of tokens")
                     temp=gr.Slider(label="Temperature",step=0.01, minimum=0.01, maximum=1.0, value=0.9)