Update app.py

app.py

@@ -303,11 +303,9 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                 value="Lumian-VLR-7B-Thinking"
             )
             gr.Markdown("**Model Info 💻** | [Report Bug](https://huggingface.co/spaces/prithivMLmods/Multimodal-VLM-Thinking/discussions)")
-            gr.Markdown("> **MiniCPM-V 4** is a powerful open-source multimodal model capable of handling various image and text-based tasks with high accuracy.")
-            gr.Markdown("> **Lumian-VLR-7B-Thinking** is a high-fidelity vision-language reasoning model built on Qwen2.5-VL-7B-Instruct, designed for fine-grained multimodal understanding, enhancing image captioning, video reasoning, and document comprehension through explicit grounded reasoning.")
-            gr.Markdown("> **olmOCR-7B-0225-preview** is a 7B parameter open large model designed for OCR tasks with robust text extraction, especially in complex document layouts. ")
-            gr.Markdown("> **Typhoon-ocr-3b** is a 3B parameter OCR model optimized for efficient and accurate optical character recognition in challenging conditions.")
-            gr.Markdown("> **DREX-062225-exp** is an experimental multimodal model emphasizing strong document reading and extraction capabilities combined with vision-language understanding to support detailed document parsing and reasoning tasks.")
+            gr.Markdown("> MiniCPM-V 4.0 is the latest efficient model in the MiniCPM-V series. The model is built based on SigLIP2-400M and MiniCPM4-3B with a total of 4.1B parameters. It inherits the strong single-image, multi-image and video understanding performance of MiniCPM-V 2.6 with largely improved efficiency. Lumian-VLR-7B-Thinking is a high-fidelity vision-language reasoning model built on Qwen2.5-VL-7B-Instruct, designed for fine-grained multimodal understanding, video reasoning, and document comprehension through explicit grounded reasoning.")
+            gr.Markdown("> olmOCR-7B-0225-preview is a 7B parameter open large model designed for OCR tasks with robust text extraction, especially in complex document layouts. Typhoon-ocr-3b is a 3B parameter OCR model optimized for efficient and accurate optical character recognition in challenging conditions.")
+            gr.Markdown("> DREX-062225-exp is an experimental multimodal model emphasizing strong document reading and extraction capabilities combined with vision-language understanding to support detailed document parsing and reasoning tasks.")
             gr.Markdown("> ⚠️ Note: Video inference performance can vary significantly between models.")
 
     image_submit.click(
@@ -322,4 +320,4 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
     )
 
 if __name__ == "__main__":
-    demo.queue(max_size=30).launch(share=True, show_error=True)
+    demo.queue(max_size=50).launch(share=True, mcp_server=True, ssr_mode=False, show_error=True)