diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_left_shift.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_left_shift.md
new file mode 100644
index 00000000000..bb10be9c733
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_left_shift.md
@@ -0,0 +1,32 @@
+## [ paddle 参数更多 ]torch.Tensor.bitwise_left_shift
+
+### [torch.Tensor.bitwise_left_shift](https://pytorch.org/docs/stable/generated/torch.Tensor.bitwise_left_shift.html#torch-tensor-bitwise-left-shift)
+
+```python
+torch.Tensor.bitwise_left_shift(other)
+```
+
+### [paddle.Tensor.bitwise_left_shift]()
+
+```python
+paddle.Tensor.bitwise_left_shift(y, is_arithmetic=True)
+```
+
+其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
+
+### 参数映射
+
+| PyTorch | PaddlePaddle  | 备注                                                                |
+| ------- | ------------- | ------------------------------------------------------------------- |
+| other   | y             | 表示输入的 Tensor ，仅参数名不一致。                                |
+| -       | is_arithmetic | 用于表明是否执行算术位移， PyTorch 无此参数， Paddle 保持默认即可。 |
+
+### 转写示例
+
+```python
+# PyTorch 写法
+out = x.bitwise_left_shift(y)
+
+# Paddle 写法
+out = x.bitwise_left_shift(y)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_left_shift_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_left_shift_.md
new file mode 100644
index 00000000000..0f2b244024a
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_left_shift_.md
@@ -0,0 +1,32 @@
+## [ paddle 参数更多 ]torch.Tensor.bitwise_left_shift_
+
+### [torch.Tensor.bitwise_left_shift_](https://pytorch.org/docs/stable/generated/torch.Tensor.bitwise_left_shift_.html#torch-tensor-bitwise-left-shift)
+
+```python
+torch.Tensor.bitwise_left_shift_(other)
+```
+
+### [paddle.Tensor.bitwise_left_shift_]()
+
+```python
+paddle.Tensor.bitwise_left_shift_(y, is_arithmetic=True)
+```
+
+其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
+
+### 参数映射
+
+| PyTorch | PaddlePaddle  | 备注                                                                |
+| ------- | ------------- | ------------------------------------------------------------------- |
+| other   | y             | 表示输入的 Tensor ，仅参数名不一致。                                |
+| -       | is_arithmetic | 用于表明是否执行算术位移， PyTorch 无此参数， Paddle 保持默认即可。 |
+
+### 转写示例
+
+```python
+# PyTorch 写法
+out = x.bitwise_left_shift_(y)
+
+# Paddle 写法
+out = x.bitwise_left_shift_(y)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_right_shift.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_right_shift.md
new file mode 100644
index 00000000000..f6951ca69f5
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_right_shift.md
@@ -0,0 +1,32 @@
+## [ paddle 参数更多 ]torch.Tensor.bitwise_right_shift
+
+### [torch.Tensor.bitwise_right_shift](https://pytorch.org/docs/stable/generated/torch.Tensor.bitwise_right_shift.html#torch-tensor-bitwise-right-shift)
+
+```python
+torch.Tensor.bitwise_right_shift(other)
+```
+
+### [paddle.Tensor.bitwise_right_shift]()
+
+```python
+paddle.Tensor.bitwise_right_shift(y, is_arithmetic=True)
+```
+
+其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
+
+### 参数映射
+
+| PyTorch | PaddlePaddle  | 备注                                                                |
+| ------- | ------------- | ------------------------------------------------------------------- |
+| other   | y             | 表示输入的 Tensor ，仅参数名不一致。                                |
+| -       | is_arithmetic | 用于表明是否执行算术位移， PyTorch 无此参数， Paddle 保持默认即可。 |
+
+### 转写示例
+
+```python
+# PyTorch 写法
+out = x.bitwise_right_shift(y)
+
+# Paddle 写法
+out = x.bitwise_right_shift(y)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_right_shift_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_right_shift_.md
new file mode 100644
index 00000000000..0b0c66d154f
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.bitwise_right_shift_.md
@@ -0,0 +1,32 @@
+## [ paddle 参数更多 ]torch.Tensor.bitwise_right_shift_
+
+### [torch.Tensor.bitwise_right_shift_](https://pytorch.org/docs/stable/generated/torch.Tensor.bitwise_right_shift_.html#torch-tensor-bitwise-right-shift)
+
+```python
+torch.Tensor.bitwise_right_shift_(other)
+```
+
+### [paddle.Tensor.bitwise_right_shift_]()
+
+```python
+paddle.Tensor.bitwise_right_shift_(y, is_arithmetic=True)
+```
+
+其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
+
+### 参数映射
+
+| PyTorch | PaddlePaddle  | 备注                                                                |
+| ------- | ------------- | ------------------------------------------------------------------- |
+| other   | y             | 表示输入的 Tensor ，仅参数名不一致。                                |
+| -       | is_arithmetic | 用于表明是否执行算术位移， PyTorch 无此参数， Paddle 保持默认即可。 |
+
+### 转写示例
+
+```python
+# PyTorch 写法
+out = x.bitwise_right_shift_(y)
+
+# Paddle 写法
+out = x.bitwise_right_shift_(y)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.col_indices.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.col_indices.md
new file mode 100644
index 00000000000..d6f2ecf7398
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.col_indices.md
@@ -0,0 +1,15 @@
+## [ 无参数 ] torch.Tensor.col_indices
+
+### [torch.Tensor.col_indices](https://pytorch.org/docs/stable/generated/torch.Tensor.col_indices.html)
+
+```python
+torch.Tensor.col_indices()
+```
+
+### [paddle.Tensor.cols]()
+
+```python
+paddle.Tensor.cols()
+```
+
+两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.crow_indices.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.crow_indices.md
new file mode 100644
index 00000000000..83f29326b54
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.crow_indices.md
@@ -0,0 +1,15 @@
+## [ 无参数 ] torch.Tensor.crow_indices
+
+### [torch.Tensor.crow_indices](https://pytorch.org/docs/stable/generated/torch.Tensor.crow_indices.html)
+
+```python
+torch.Tensor.crow_indices()
+```
+
+### [paddle.Tensor.crows]()
+
+```python
+paddle.Tensor.crows()
+```
+
+两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.data_ptr.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.data_ptr.md
new file mode 100644
index 00000000000..41909acfb0f
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.data_ptr.md
@@ -0,0 +1,15 @@
+## [ 无参数 ] torch.Tensor.data_ptr
+
+### [torch.Tensor.data_ptr](https://pytorch.org/docs/stable/generated/torch.Tensor.data_ptr.html)
+
+```python
+torch.Tensor.data_ptr()
+```
+
+### [paddle.Tensor.data_ptr](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html)
+
+```python
+paddle.Tensor.data_ptr()
+```
+
+两者功能一致。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.dim_order.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.dim_order.md
new file mode 100644
index 00000000000..a71aa26a485
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.dim_order.md
@@ -0,0 +1,19 @@
+## [ 组合替代实现 ] torch.Tensor.dim_order
+
+### [torch.Tensor.dim_order](https://pytorch.org/docs/stable/generated/torch.Tensor.dim_order.html?highlight=dim_order#torch.Tensor.dim_order)
+
+```python
+torch.Tensor.dim_order()
+```
+
+Paddle 无此 API，需要组合实现。获取张量在内存中的物理布局，PaddlePaddle 的 Tensor 默认是 contiguous 的, 因此可直接返回一个从 0 到 Tensor 的维度长度的列表即可。
+
+### 转写示例
+
+```python
+# PyTorch 写法
+y = x.dim_order()
+
+# Paddle 写法
+y = tuple([i for i in range(len(x.shape))])
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_sparse_csr.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_sparse_csr.md
new file mode 100644
index 00000000000..5d29dc300a3
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_sparse_csr.md
@@ -0,0 +1,25 @@
+## [ 无参数 ] torch.Tensor.is_sparse_csr
+
+### [torch.Tensor.is_sparse_csr](https://pytorch.org/docs/stable/generated/torch.Tensor.is_sparse_csr.html)
+
+```python
+torch.Tensor.is_sparse_csr
+```
+
+### [paddle.Tensor.is_sparse_csr](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html)
+
+```python
+paddle.Tensor.is_sparse_csr()
+```
+
+两者功能一致，但使用方式不一致，前者可以直接访问属性，后者需要调用方法，具体如下：
+
+### 转写示例
+
+```python
+# torch 版本可以直接访问属性
+x.is_sparse_csr
+
+# Paddle 版本需要调用
+x.is_sparse_csr()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.itemsize.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.itemsize.md
new file mode 100644
index 00000000000..8e56dd2dea0
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.itemsize.md
@@ -0,0 +1,15 @@
+## [ 无参数 ]torch.Tensor.item_size
+
+### [torch.Tensor.item_size](https://pytorch.org/docs/stable/generated/torch.Tensor.itemsize.html)
+
+```python
+torch.Tensor.item_size()
+```
+
+### [paddle.Tensor.element_size](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#element-size)
+
+```python
+paddle.Tensor.element_size()
+```
+
+两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.nbytes.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.nbytes.md
new file mode 100644
index 00000000000..34f171c46b9
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.nbytes.md
@@ -0,0 +1,19 @@
+## [ 组合替代实现 ]torch.Tensor.nbytes
+
+### [torch.Tensor.nbytes](https://pytorch.org/docs/stable/generated/torch.Tensor.nbytes.html)
+
+```python
+torch.Tensor.nbytes
+```
+
+Paddle 无此 API，需要组合实现。
+
+### 转写示例
+
+```python
+# PyTorch 写法
+y = a.nbytes
+
+# Paddle 写法
+y = a.size * a.element_size()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.stride.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.stride.md
new file mode 100644
index 00000000000..82f800a5293
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.stride.md
@@ -0,0 +1,35 @@
+## [ torch 参数更多 ] torch.Tensor.stride
+
+### [torch.Tensor.stride](https://pytorch.org/docs/stable/generated/torch.Tensor.stride.html#torch-tensor-stride)
+
+```python
+torch.Tensor.stride(dim=None)
+```
+
+### [paddle.Tensor.get_strides](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#tensor)
+
+```python
+paddle.Tensor.get_strides()
+```
+
+PyTorch 相比 Paddle 支持更多其他参数，具体如下：
+
+### 参数映射
+
+
+| PyTorch | PaddlePaddle | 备注                                                                                          |
+| ------- | ------------ | --------------------------------------------------------------------------------------------- |
+| dim     | -            | 返回指定维度的步长， Pytorch 为可选值，默认返回全部步长，此时无需转写，当有输入值时，需要转写。 |
+
+### 转写示例
+
+```python
+# torch 版本, 默认返回全部
+x.stride(dim=None)
+
+# Paddle 版本
+if dim is not None:
+    x.get_strides()[dim]
+else:
+    x.get_strides()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.to_sparse_coo.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.to_sparse_coo.md
new file mode 100644
index 00000000000..739d6833be8
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.to_sparse_coo.md
@@ -0,0 +1,22 @@
+## [ paddle 参数更多 ]torch.Tensor.to_sparse_coo
+
+### [torch.Tensor.to_sparse_coo](https://pytorch.org/docs/stable/generated/torch.Tensor.to_sparse_coo.html)
+
+```python
+torch.Tensor.to_sparse_coo()
+```
+
+### [paddle.Tensor.to_sparse_coo]()
+
+```python
+paddle.Tensor.to_sparse_coo(sparse_dim)
+```
+
+其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
+
+### 参数映射
+
+
+| PyTorch | PaddlePaddle | 备注                                                                                          |
+| ------- | ------------ | --------------------------------------------------------------------------------------------- |
+| -       | sparse_dim   | 在新的稀疏张量中包含的稀疏维度的数量，pytorch 中无此参数，paddle 令其为 tensor 输入维度即可。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch/torch.bitwise_left_shift.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch/torch.bitwise_left_shift.md
new file mode 100644
index 00000000000..8e7926fa3f2
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch/torch.bitwise_left_shift.md
@@ -0,0 +1,24 @@
+## [ paddle 参数更多 ]torch.bitwise_left_shift
+
+### [torch.bitwise_left_shift](https://pytorch.org/docs/stable/generated/torch.bitwise_left_shift.html)
+
+```python
+torch.bitwise_left_shift(input, other, *, out=None)
+```
+
+### [paddle.bitwise_left_shift](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/bitwise_left_shift_cn.html#bitwise-left-shift)
+
+```python
+paddle.bitwise_left_shift(x, y, is_arithmetic=True, out=None, name=None)
+```
+
+其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
+
+### 参数映射
+
+| PyTorch | PaddlePaddle  | 备注                                                                |
+| ------- | ------------- | ------------------------------------------------------------------- |
+| input   | x             | 表示输入的 Tensor ，仅参数名不一致。                                |
+| other   | y             | 表示输入的 Tensor ，仅参数名不一致。                                |
+| out     | out           | 表示输出的 Tensor。                                                 |
+| -       | is_arithmetic | 用于表明是否执行算术位移， PyTorch 无此参数， Paddle 保持默认即可。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch/torch.bitwise_right_shift.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch/torch.bitwise_right_shift.md
new file mode 100644
index 00000000000..c301fc5a992
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch/torch.bitwise_right_shift.md
@@ -0,0 +1,24 @@
+## [ paddle 参数更多 ]torch.bitwise_right_shift
+
+### [torch.bitwise_right_shift](https://pytorch.org/docs/stable/generated/torch.bitwise_right_shift.html)
+
+```python
+torch.bitwise_right_shift(input, other, *, out=None)
+```
+
+### [paddle.bitwise_right_shift](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/bitwise_right_shift_cn.html#bitwise-right-shift)
+
+```python
+paddle.bitwise_right_shift(x, y, is_arithmetic=True, out=None, name=None)
+```
+
+其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
+
+### 参数映射
+
+| PyTorch | PaddlePaddle  | 备注                                                                |
+| ------- | ------------- | ------------------------------------------------------------------- |
+| input   | x             | 表示输入的 Tensor ，仅参数名不一致。                                |
+| other   | y             | 表示输入的 Tensor ，仅参数名不一致。                                |
+| out     | out           | 表示输出的 Tensor。                                                 |
+| -       | is_arithmetic | 用于表明是否执行算术位移， PyTorch 无此参数， Paddle 保持默认即可。 |