use gradio 5

app.py

@@ -139,7 +139,7 @@ custom_theme = gr.themes.Soft(
 )
 
 # Build the Gradio interface
-with gr.Blocks() as demo:
+with gr.Blocks(theme=custom_theme) as demo:
     gr.Markdown(
         """
         # 🤖 Smol LLM Inference GUI
@@ -235,14 +235,12 @@ with gr.Blocks() as demo:
             repetition_penalty,
             system_prompt
         ],
-        outputs=[output_text],
-        api_visibility="public"
+        outputs=[output_text]
     )
     
     clear_btn.click(
         fn=clear_chat,
-        outputs=[prompt_input, output_text],
-        api_visibility="private"
+        outputs=[prompt_input, output_text]
     )
     
     # Allow Enter key to generate
@@ -256,8 +254,7 @@ with gr.Blocks() as demo:
             repetition_penalty,
             system_prompt
         ],
-        outputs=[output_text],
-        api_visibility="public"
+        outputs=[output_text]
     )
 
 # Auto-load the model at startup
@@ -266,13 +263,6 @@ print(f"Startup load status: {load_status}")
 
 # Launch the application
 demo.launch(
-    theme=custom_theme,
-    footer_links=[
-        {"label": "Built with anycoder", "url": "https://huggingface.co/spaces/akhaliq/anycoder"},
-        {"label": "SmolLM2 Model", "url": "https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct"},
-        {"label": "Gradio", "url": "https://gradio.app"}
-    ],
     share=False,
-    show_error=True,
-    ssr_mode=False
+    show_error=True
 )

requirements.txt

@@ -1,4 +1,4 @@
 accelerate
 torch
 transformers
-gradio
+gradio==5.9.0