Update app.py

app.py

@@ -17,7 +17,7 @@ def load_models():
     model = Qwen2VLForConditionalGeneration.from_pretrained(
         "Qwen/Qwen2-VL-2B-Instruct",
         trust_remote_code=True, 
-        torch_dtype=torch.bfloat16).cuda().eval()
+        torch_dtype=torch.bfloat16).eval()
     
     processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", trust_remote_code=True)
     
@@ -65,7 +65,8 @@ if uploaded_file is not None:
         padding=True,
         return_tensors="pt",
     )
-    inputs = inputs.to("cuda")
+    inputs = inputs.to("cpu")
+
 
     # Generate the text from the image using the model
     generated_ids = model.generate(**inputs, max_new_tokens=5000)
@@ -142,7 +143,7 @@ if uploaded_file is not None:
                     padding=True,
                     return_tensors="pt",
                 )
-                inputs = inputs.to("cuda")
+                inputs = inputs.to("cpu")
                 
                 generated_ids_query = model.generate(**inputs, max_new_tokens=1000)
                 generated_ids_trimmed = [