Update app.py

app.py

@@ -4,6 +4,7 @@ from PIL import Image
 from transformers import AutoModel, AutoTokenizer
 import warnings
 import os
+import spaces
 
 # 禁用警告信息
 warnings.filterwarnings("ignore")
@@ -12,21 +13,22 @@ warnings.filterwarnings("ignore")
 model = None
 tokenizer = None
 
+@spaces.GPU
 def load_model():
     """加载MiniCPM-o模型"""
     global model, tokenizer
     if model is None:
         print("正在加载MiniCPM-o模型...")
+        device = "cuda" if torch.cuda.is_available() else "cpu"
         model = AutoModel.from_pretrained(
             'openbmb/MiniCPM-o-2_6',
             trust_remote_code=True,
-            attn_implementation='sdpa',
-            torch_dtype=torch.bfloat16,
+            torch_dtype=torch.bfloat16 if device == "cuda" else torch.float32,
             init_vision=True,
             init_audio=False,
             init_tts=False
         )
-        model = model.eval().cuda()
+        model = model.eval().to(device)
         tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-o-2_6', trust_remote_code=True)
         print("模型加载完成")
     return model, tokenizer
@@ -133,6 +135,7 @@ def clean_text_output(text):
     
     return '\n'.join(text_lines)
 
+@spaces.GPU
 def parse_image(image, parse_type):
     """解析图片内容为指定格式"""
     try:
@@ -298,13 +301,9 @@ def create_interface():
     return interface
 
 if __name__ == "__main__":
-    # 预加载模型（可选，在启动时加载以减少首次使用延迟）
-    try:
-        load_model()
-        print("✅ 模型预加载完成")
-    except Exception as e:
-        print(f"⚠️ 模型预加载失败: {e}")
-        print("模型将在首次使用时加载")
+    # 在ZeroGPU环境中不预加载模型，按需加载以节省资源
+    print("🚀 启动MiniCPM多模态内容解析工具")
+    print("📝 模型将在首次使用时自动加载")
     
     # 创建并启动界面
     interface = create_interface()