diff --git a/python/paddle/amp/debugging.py b/python/paddle/amp/debugging.py
index 1b6e575cdbec9..8b4340a2c4935 100644
--- a/python/paddle/amp/debugging.py
+++ b/python/paddle/amp/debugging.py
@@ -88,7 +88,7 @@ def check_layer_numerics(func):
             ...         return x @ self._w + self._b
             ...
             >>> dtype = 'float32'
-            >>> x = paddle.rand([10, 2, 2], dtype=dtype) # type: ignore
+            >>> x = paddle.rand([10, 2, 2], dtype=dtype) # type: ignore[arg-type]
             >>> model = MyLayer(dtype)
             >>> x[0] = float(0)
             >>> loss = model(x)
diff --git a/python/paddle/base/layers/math_op_patch.py b/python/paddle/base/layers/math_op_patch.py
index 1dd3c19b44d9a..dfd4c802d89f9 100644
--- a/python/paddle/base/layers/math_op_patch.py
+++ b/python/paddle/base/layers/math_op_patch.py
@@ -352,7 +352,7 @@ def astype(self, dtype):
                 >>> import paddle
                 >>> import numpy as np
 
-                >>> x = np.ones([2, 2], np.float32)
+                >>> x = np.ones([2, 2], np.float32) # type: ignore[var-annotated]
                 >>> with base.dygraph.guard():
                 ...     original_variable = paddle.to_tensor(x)
                 ...     print("original var's dtype is: {}, numpy dtype is {}".format(original_variable.dtype, original_variable.numpy().dtype))
diff --git a/python/paddle/distributed/communication/stream/gather.py b/python/paddle/distributed/communication/stream/gather.py
index c0405ec696bc0..45b86b0215e0f 100644
--- a/python/paddle/distributed/communication/stream/gather.py
+++ b/python/paddle/distributed/communication/stream/gather.py
@@ -83,7 +83,7 @@ def gather(
             >>> import paddle.distributed as dist
 
             >>> dist.init_parallel_env()
-            >>> gather_list = []
+            >>> gather_list = [] # type: ignore[var-annotated]
             >>> if dist.get_rank() == 0:
             ...     data = paddle.to_tensor([1, 2, 3])
             ...     dist.stream.gather(data, gather_list, dst=0)
diff --git a/python/paddle/distributed/parallel.py b/python/paddle/distributed/parallel.py
index 0d905b4f5d985..791f8834c37a6 100644
--- a/python/paddle/distributed/parallel.py
+++ b/python/paddle/distributed/parallel.py
@@ -334,7 +334,7 @@ class DataParallel(layers.Layer):
             ...     model = paddle.DataParallel(model)
             ...     opt = paddle.optimizer.SGD(learning_rate=0.01, parameters=model.parameters())
             ...     for step in range(10):
-            ...         x_data = numpy.random.randn(2, 2).astype(numpy.float32)
+            ...         x_data = numpy.random.randn(2, 2).astype(numpy.float32) # type: ignore[var-annotated]
             ...         x = paddle.to_tensor(x_data)
             ...         x.stop_gradient = False
             ...         # step 1 : skip gradient synchronization by 'no_sync'
diff --git a/python/paddle/optimizer/lbfgs.py b/python/paddle/optimizer/lbfgs.py
index a0198048ecfea..5a41e119f08bf 100644
--- a/python/paddle/optimizer/lbfgs.py
+++ b/python/paddle/optimizer/lbfgs.py
@@ -399,10 +399,10 @@ class LBFGS(Optimizer):
 
             >>> paddle.disable_static()
             >>> np.random.seed(0)
-            >>> np_w = np.random.rand(1).astype(np.float32)  # type: ignore
-            >>> np_x = np.random.rand(1).astype(np.float32)  # type: ignore
+            >>> np_w = np.random.rand(1).astype(np.float32)  # type: ignore[var-annotated]
+            >>> np_x = np.random.rand(1).astype(np.float32)  # type: ignore[var-annotated]
 
-            >>> inputs = [np.random.rand(1).astype(np.float32) for i in range(10)]  # type: ignore
+            >>> inputs = [np.random.rand(1).astype(np.float32) for i in range(10)]  # type: ignore[var-annotated]
             >>> # y = 2x
             >>> targets = [2 * x for x in inputs]
 
diff --git a/python/paddle/tensor/attribute.py b/python/paddle/tensor/attribute.py
index 2a0f4f5df2eed..d4d35bcb1e05a 100644
--- a/python/paddle/tensor/attribute.py
+++ b/python/paddle/tensor/attribute.py
@@ -102,7 +102,7 @@ def shape(input: Tensor) -> Tensor:
             >>> exe = paddle.static.Executor(paddle.CPUPlace())
             >>> exe.run(paddle.static.default_startup_program())
 
-            >>> img = np.ones((3, 100, 100)).astype(np.float32) # type: ignore
+            >>> img = np.ones((3, 100, 100)).astype(np.float32) # type: ignore[var-annotated]
 
             >>> res = exe.run(paddle.static.default_main_program(), feed={'x':img}, fetch_list=[output])
             >>> print(res)
diff --git a/python/paddle/tensor/creation.py b/python/paddle/tensor/creation.py
index 506525d1e2e49..8e6635a641f62 100644
--- a/python/paddle/tensor/creation.py
+++ b/python/paddle/tensor/creation.py
@@ -2483,7 +2483,7 @@ def assign(x: TensorLike, output: paddle.Tensor | None = None) -> paddle.Tensor:
              [2.5 2.5]]
             >>> array = np.array([[1, 1], [3, 4], [1, 3]]).astype(
             ...     np.int64
-            ... )  # type: ignore
+            ... )  # type: ignore[var-annotated]
             >>> result1 = paddle.zeros(shape=[3, 3], dtype='float32')
             >>> paddle.assign(array, result1)
             >>> print(result1.numpy())
diff --git a/python/paddle/vision/transforms/transforms.py b/python/paddle/vision/transforms/transforms.py
index bf5fc470e87f3..2e25cbc76e164 100644
--- a/python/paddle/vision/transforms/transforms.py
+++ b/python/paddle/vision/transforms/transforms.py
@@ -232,7 +232,7 @@ class BaseTransform(_Transform[_InputT, _RetT]):
             ...     else:
             ...         raise TypeError("Unexpected type {}".format(type(img)))
             ...
-            >>> class CustomRandomFlip(BaseTransform): # type: ignore
+            >>> class CustomRandomFlip(BaseTransform): # type: ignore[type-arg]
             ...     def __init__(self, prob=0.5, keys=None):
             ...         super().__init__(keys)
             ...         self.prob = prob