Update app.py

app.py

@@ -106,7 +106,7 @@ def model_inference(input_dict, history):
         thread = Thread(target=model.generate, kwargs=generation_kwargs)
         thread.start()
         buffer = ""
-        yield progress_bar_html("Processing video with Qwen2.5VL Model")
+        yield progress_bar_html("Processing video with MiMo-VL-7B-RL Model")
         for new_text in streamer:
             buffer += new_text
             time.sleep(0.01)
@@ -148,7 +148,7 @@ def model_inference(input_dict, history):
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()
     buffer = ""
-    yield progress_bar_html("Processing with Qwen2.5VL Model")
+    yield progress_bar_html("Processing with MiMo-VL-7B-RL Model")
     for new_text in streamer:
         buffer += new_text
         time.sleep(0.01)
@@ -156,9 +156,8 @@ def model_inference(input_dict, history):
 
 examples = [
     [{"text": "Describe the Image?", "files": ["example_images/document.jpg"]}],
-    [{"text": "@video-infer Explain the content of the Advertisement", "files": ["example_images/videoplayback.mp4"]}],
-    [{"text": "@video-infer Explain the content of the video in detail", "files": ["example_images/breakfast.mp4"]}],
-    [{"text": "@video-infer Explain the content of the video.", "files": ["example_images/sky.mp4"]}],
+    [{"text": "How many dog in the image?", "files": ["example_images/dogs.jpg"]}],
+    [{"text": "How many dog in the image? Count the dog by grounding. Put the numberin \\boxed{}", "files": ["example_images/dogs.jpg"]}],
 ]
 
 demo = gr.ChatInterface(