Update app.py

app.py

@@ -13,6 +13,9 @@ import gradio as gr
 
 from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
 
+
+### Load the model and helper functions ### 
+
 model_path = "Qwen/Qwen2.5-VL-7B-Instruct"
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_path,
                                                            torch_dtype=torch.bfloat16,
@@ -305,7 +308,8 @@ def numpy_to_pil(numpy_array):
 
     return pil_image
 
-# prompt = "Outline the position and names of each unique edible food and drink item and output all the coordinates in JSON format. Only outline food and drink items that are edible."
+### Prompt section ###
+
 prompt_thinking = """Outline the bounding box coordinates and names of each unique edible food and drink item and output all the coordinates in JSON format.
 Only outline food and drink items that are edible.
 Ignore hard to see items in the background. Only focus on the foreground.