Upload 3 files

app.py

@@ -16,10 +16,8 @@ processor = AutoProcessor.from_pretrained(MODEL_ID)
 # Load Model
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     MODEL_ID, 
-    torch_dtype=torch.float16,
-    device_map="auto"
-)
-model.eval()
+    torch_dtype=torch.float16
+).to(device).eval()
 print("Model loaded.")
 
 @spaces.GPU