Update app.py

app.py

@@ -54,15 +54,15 @@ def downsample_video(video_path):
     vidcap.release()
     return frames
 
-# MODEL_ID = "XiaomiMiMo/MiMo-VL-7B-RL"  # Alternatively: "XiaomiMiMo/MiMo-VL-7B-RL" 
-MODEL_ID = "Qwen/Qwen2.5-VL-7B-Instruct"  # Alternatively: "XiaomiMiMo/MiMo-VL-7B-RL" 
+MODEL_ID = "XiaomiMiMo/MiMo-VL-7B-RL"  # Alternatively: "XiaomiMiMo/MiMo-VL-7B-RL" 
+# MODEL_ID = "Qwen/Qwen2.5-VL-7B-Instruct"  # Alternatively: "XiaomiMiMo/MiMo-VL-7B-RL" 
 processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     MODEL_ID,
     trust_remote_code=True,
     torch_dtype=torch.bfloat16
 ).to("cuda").eval()
-
+print(f"Successfully load the model: {model}")
 @spaces.GPU
 def model_inference(input_dict, history):
     text = input_dict["text"]