Update app.py

app.py

@@ -124,7 +124,7 @@ model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     torch_dtype=torch.bfloat16
 ).to("cuda").eval()
 
-@spaces.GPU
+@spaces.GPU(duration=200)
 def model_inference(input_dict, history):
     text = input_dict["text"]
     files = input_dict["files"]
@@ -181,10 +181,14 @@ def model_inference(input_dict, history):
         time.sleep(0.01)
         yield buffer
 
+examples = [
+    [{"text": "Hint: Please answer the question and provide the final answer at the end. Question: Which number do you have to write in the last daisy?", "files": ["5.jpg"]}]
+]
 
 demo = gr.ChatInterface(
     fn=model_inference,
-    description="# **Fancy-MLLM/R1-OneVision-7B**",
+    description="# **🦖 Fancy-MLLM/R1-OneVision-7B**",
+    examples=examples,
     textbox=gr.MultimodalTextbox(label="Query Input", file_types=["image"], file_count="multiple"),
     stop_btn="Stop Generation",
     multimodal=True,
@@ -192,3 +196,4 @@ demo = gr.ChatInterface(
 )
 
 demo.launch(debug=True)
+