Update app.py

app.py

@@ -8,7 +8,7 @@ import os
 
 # subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
-DESCRIPTION = "[Sparrow Qwen2-VL-2.5B Backend](https://github.com/katanaml/sparrow)"
+DESCRIPTION = "[Sparrow Qwen2-VL-2B Backend](https://github.com/katanaml/sparrow)"
 
 
 def array_to_image_path(image_filepath, max_width=1250, max_height=1750):
@@ -61,12 +61,12 @@ def array_to_image_path(image_filepath, max_width=1250, max_height=1750):
 
 # Initialize the model and processor globally to optimize performance
 model = Qwen2VLForConditionalGeneration.from_pretrained(
-    "Qwen/Qwen2-VL-2.5B-Instruct",
+    "Qwen/Qwen2-VL-2B-Instruct",
     torch_dtype="auto",
     device_map="auto"
 )
 
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2.5B-Instruct")
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
 
 
 @spaces.GPU
@@ -140,7 +140,7 @@ css = """
 
 with gr.Blocks(css=css) as demo:
     gr.Markdown(DESCRIPTION)
-    with gr.Tab(label="Qwen2-VL-2.5B Input"):
+    with gr.Tab(label="Qwen2-VL-2B Input"):
         with gr.Row():
             with gr.Column():
                 input_imgs = gr.Files(file_types=["image"], label="Upload Document Images")