Update app.py

app.py

@@ -13,9 +13,9 @@ def respond(
     message,
     history: list[tuple[str, str]],
     system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    # max_tokens,
+    # temperature,
+    # top_p,
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -32,9 +32,9 @@ def respond(
         model="nvidia/llama-3.1-nemotron-70b-instruct",
         messages=messages,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
-        max_tokens=max_tokens,
+        # temperature=temperature,
+        # top_p=top_p,
+        # max_tokens=max_tokens,
     )
 
     for message in completion:
@@ -59,15 +59,15 @@ with gr.Blocks() as demo:
                 respond,
                 additional_inputs=[
                     gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-                    gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-                    gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-                    gr.Slider(
-                        minimum=0.1,
-                        maximum=1.0,
-                        value=0.95,
-                        step=0.05,
-                        label="Top-p (nucleus sampling)",
-                    ),
+                    # gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+                    # gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+                    # gr.Slider(
+                    #     minimum=0.1,
+                    #     maximum=1.0,
+                    #     value=0.95,
+                    #     step=0.05,
+                    #     label="Top-p (nucleus sampling)",
+                    # ),
                 ],
             )
         else: