update app

app.py

@@ -107,7 +107,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 
 model = AutoModel.from_pretrained(
     model_name,
-    #_attn_implementation="flash_attention_2",
+    _attn_implementation="flash_attention_2",
     trust_remote_code=True,
     use_safetensors=True,
 ).to(device).eval() # Move to device and set to eval mode
@@ -211,7 +211,7 @@ def process_ocr_task(image, model_size, task_type, ref_text):
 with gr.Blocks(css=css, theme=steel_blue_theme) as demo:
     gr.Markdown("# **DeepSeek OCR [exp]**", elem_id="main-title")
 
-
+    
     with gr.Row():
         with gr.Column(scale=1):
             image_input = gr.Image(type="pil", label="Upload Image", sources=["upload", "clipboard"])
@@ -223,10 +223,10 @@ with gr.Blocks(css=css, theme=steel_blue_theme) as demo:
         with gr.Column(scale=2):
             output_text = gr.Textbox(label="Output (OCR)", lines=8, show_copy_button=True)
             output_image = gr.Image(label="Layout Detection (If Any)", type="pil")
-
+            
             with gr.Accordion("Note", open=False):
                 gr.Markdown("Inference using Huggingface transformers on NVIDIA GPUs. This app is running with transformers version 4.57.1 and torch version 2.6.0.")
-
+                
     def toggle_ref_text_visibility(task):
         return gr.Textbox(visible=True) if task == "Locate Object by Reference" else gr.Textbox(visible=False)
 
@@ -234,4 +234,4 @@ with gr.Blocks(css=css, theme=steel_blue_theme) as demo:
     submit_btn.click(fn=process_ocr_task, inputs=[image_input, model_size, task_type, ref_text_input], outputs=[output_text, output_image])
 
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch(share=True)
+    demo.queue(max_size=20).launch(share=True, mcp_server=True, ssr_mode=False)