diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.arctanh.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.arctanh.md
index fb62a8d0cce..f3da848166e 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.arctanh.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.arctanh.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.arctanh](https://pytorch.org/docs/stable/generated/torch.Tensor.arctanh.html#torch.Tensor.arctanh)
 
-```
+```python
 torch.Tensor.arctanh()
 ```
 
 ### [paddle.Tensor.atanh]()
 
-```
+```python
 paddle.Tensor.atanh()
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.arctanh_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.arctanh_.md
index 34e442b56ac..74279293b62 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.arctanh_.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.arctanh_.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.arctanh_](https://pytorch.org/docs/stable/generated/torch.Tensor.arctanh_.html)
 
-```
+```python
 torch.Tensor.arctanh_()
 ```
 
 ### [paddle.Tensor.atanh_]()
 
-```
+```python
 paddle.Tensor.atanh_()
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.atanh.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.atanh.md
index bca7344dffc..5489807bbc2 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.atanh.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.atanh.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.atanh](https://pytorch.org/docs/stable/generated/torch.Tensor.atanh.html#torch.Tensor.atanh)
 
-```
+```python
 torch.Tensor.atanh()
 ```
 
 ### [paddle.Tensor.atanh]()
 
-```
+```python
 paddle.Tensor.atanh()
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.atanh_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.atanh_.md
index 9a543f502d3..8e7f20a39ee 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.atanh_.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.atanh_.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.atanh_](https://pytorch.org/docs/stable/generated/torch.Tensor.atanh_.html#torch.Tensor.atanh_)
 
-```
+```python
 torch.Tensor.atanh_()
 ```
 
 ### [paddle.Tensor.atanh_]()
 
-```
+```python
 paddle.Tensor.atanh_()
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_contiguous.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_contiguous.md
index 8b79a71875a..e5b1adab428 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_contiguous.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_contiguous.md
@@ -2,7 +2,7 @@
 
 ### [torch.Tensor.is_contiguous](https://pytorch.org/docs/stable/generated/torch.Tensor.is_contiguous.html#torch-tensor-is-contiguous)
 
-```
+```python
 torch.Tensor.is_contiguous(memory_format=torch.contiguous_format)
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_cuda.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_cuda.md
index ce8cf751514..a95be80ad47 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_cuda.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_cuda.md
@@ -2,7 +2,7 @@
 
 ### [torch.Tensor.is_cuda](https://pytorch.org/docs/stable/generated/torch.Tensor.is_cuda.html?highlight=is_cuda#torch.Tensor.is_cuda)
 
-```
+```python
 torch.Tensor.is_cuda
 ```
 
@@ -10,7 +10,7 @@ torch.Tensor.is_cuda
 
 ### 转写示例
 
-```
+```python
 # PyTorch 写法
 d = torch.Tensor([1,2,3])
 d.is_cuda
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_sparse.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_sparse.md
index e1092e488d6..1393779c8ea 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_sparse.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.is_sparse.md
@@ -15,7 +15,8 @@ paddle.Tensor.is_sparse()
 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 = torch.rand(3)
 # print(x.is_sparse)
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.scatter.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.scatter.md
index 6144608a3f4..3a0b3197474 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.scatter.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.scatter.md
@@ -10,7 +10,6 @@ torch.Tensor.scatter(dim, index, src, reduce=None)
 
 ```python
 paddle.Tensor.put_along_axis(indices, values, axis, reduce="assign", include_self=True, broadcast=True)
-
 ```
 
 其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.scatter_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.scatter_.md
index 8540fd77e82..af8d055b1f8 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.scatter_.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.scatter_.md
@@ -10,7 +10,6 @@ torch.Tensor.scatter_(dim, index, src)
 
 ```python
 paddle.Tensor.put_along_axis_(index, value, axis, reduce="assign", include_self=True)
-
 ```
 
 其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.take.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.take.md
index 19619df5a26..3c4467b85b1 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.take.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.take.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.take](https://pytorch.org/docs/stable/generated/torch.Tensor.take.html#torch.Tensor.take)
 
-```
+```python
 torch.Tensor.take(indices)
 ```
 
 ### [paddle.Tensor.take](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#take-index-mode-raise-name-none)
 
-```
+```python
 paddle.Tensor.take(index, mode='raise', name=None)
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tan.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tan.md
index b798da1014a..ed6c896330a 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tan.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tan.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.tan](https://pytorch.org/docs/stable/generated/torch.Tensor.tan.html#torch.Tensor.tan)
 
-```
+```python
 torch.Tensor.tan()
 ```
 
 ### [paddle.Tensor.tan]()
 
-```
+```python
 paddle.Tensor.tan()
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tanh.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tanh.md
index 9e88bdfb03e..514297cf873 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tanh.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tanh.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.tanh](https://pytorch.org/docs/stable/generated/torch.Tensor.tanh.html#torch.Tensor.tanh)
 
-```
+```python
 torch.Tensor.tanh()
 ```
 
 ### [paddle.Tensor.tanh](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#tanh-name-none)
 
-```
+```python
 paddle.Tensor.tanh()
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tanh_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tanh_.md
index 6ad79d7d099..80bdd1e2223 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tanh_.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tanh_.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.tanh_](https://pytorch.org/docs/stable/generated/torch.Tensor.tanh_.html#torch.Tensor.tanh_)
 
-```
+```python
 torch.Tensor.tanh_()
 ```
 
 ### [paddle.Tensor.tanh_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#id22)
 
-```
+```python
 paddle.Tensor.tanh_()
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tile.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tile.md
index 8159494fb83..94f44d94e11 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tile.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tile.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.tile](https://pytorch.org/docs/stable/generated/torch.Tensor.tile.html#torch.Tensor.tile)
 
-```
+```python
 torch.Tensor.tile(*reps)
 ```
 
 ### [paddle.Tensor.tile](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#tile-repeat-times-name-none)
 
-```
+```python
 paddle.Tensor.tile(repeat_times, name=None)
 ```
 
@@ -24,7 +24,7 @@ paddle.Tensor.tile(repeat_times, name=None)
 
 #### ***reps: 维度复制次数**
 
-```
+```python
 # PyTorch 写法
 x = torch.tensor([1, 2, 3])
 x.tile(2,3)
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.to_sparse.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.to_sparse.md
index 6277def49d0..277b09b035e 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.to_sparse.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.to_sparse.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.to_sparse](https://pytorch.org/docs/stable/generated/torch.Tensor.to_sparse.html#torch.Tensor.to_sparse)
 
-```
+```python
 torch.Tensor.to_sparse(sparseDims)
 ```
 
 ### [paddle.Tensor.to_sparse_coo]()
 
-```
+```python
 paddle.Tensor.to_sparse_coo(sparseDims)
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tolist.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tolist.md
index e4815b6868f..616cced334e 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tolist.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.tolist.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.tolist](https://pytorch.org/docs/stable/generated/torch.Tensor.tolist.html#torch.Tensor.tolist)
 
-```
+```python
 torch.Tensor.tolist()
 ```
 
 ### [paddle.Tensor.tolist](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#tolist)
 
-```
+```python
 paddle.Tensor.tolist()
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.topk.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.topk.md
index b0871b48911..93786434dab 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.topk.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.topk.md
@@ -2,13 +2,13 @@
 
 ### [torch.Tensor.topk](https://pytorch.org/docs/stable/generated/torch.Tensor.topk.html#torch.Tensor.topk)
 
-```
+```python
 torch.Tensor.topk(k, dim=None, largest=True, sorted=True)
 ```
 
 ### [paddle.Tensor.topk](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#topk-k-axis-none-largest-true-sorted-true-name-none)
 
-```
+```python
 paddle.Tensor.topk(k, axis=None, largest=True, sorted=True, name=None)
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.unsqueeze.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.unsqueeze.md
index f49c45d3fc9..34599af5637 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.unsqueeze.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/Tensor/torch.Tensor.unsqueeze.md
@@ -8,7 +8,7 @@ torch.Tensor.unsqueeze(dim)
 
 ### [paddle.Tensor.unsqueeze](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#unsqueeze-axis-name-none)
 
-```
+```python
 paddle.Tensor.unsqueeze(axis, name=None)
 ```
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/functional/torch.nn.functional.cross_entropy.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/functional/torch.nn.functional.cross_entropy.md
index 0dc8a334698..7d0074b3400 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/functional/torch.nn.functional.cross_entropy.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/functional/torch.nn.functional.cross_entropy.md
@@ -43,17 +43,19 @@ paddle.nn.functional.cross_entropy(input,
 
 ### 转写示例
 #### size_average
+
 size_average 为 True
+
 ```python
 # PyTorch 写法
 torch.nn.functional.cross_entropy(x,y,size_average=True)
 
 # Paddle 写法
 paddle.nn.functional.cross_entropy(x,y,reduction='mean')
-
 ```
 
 size_average 为 False
+
 ```python
 # PyTorch 写法
 torch.nn.functional.cross_entropy(x,y,size_average=False)
@@ -63,7 +65,9 @@ paddle.nn.functional.cross_entropy(x,y,reduction='sum')
 ```
 
 #### reduce
+
 reduce 为 True
+
 ```python
 # PyTorch 写法
 torch.nn.functional.cross_entropy(x,y,reduce=True)
@@ -73,6 +77,7 @@ paddle.nn.BCEWithLogitsLoss(reduction='mean')
 ```
 
 reduce 为 False
+
 ```python
 # PyTorch 写法
 torch.nn.functional.cross_entropy(x,y,reduce=False)
@@ -82,7 +87,9 @@ paddle.nn.BCEWithLogitsLoss(reduction='none')
 ```
 
 #### reduction
+
 reduction 为'none'
+
 ```python
 # PyTorch 写法
 torch.nn.functional.cross_entropy(x,y,reduction='none')
@@ -92,6 +99,7 @@ paddle.nn.functional.cross_entropy(x,y,reduction='none')
 ```
 
 reduction 为'mean'
+
 ```python
 # PyTorch 写法
 torch.nn.functional.cross_entropy(x,y,reduction='mean')
@@ -101,6 +109,7 @@ paddle.nn.functional.cross_entropy(x,y,reduction='mean')
 ```
 
 reduction 为'sum'
+
 ```python
 # PyTorch 写法
 torch.nn.functional.cross_entropy(x,y,reduction='sum')
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/functional/torch.nn.functional.kl_div.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/functional/torch.nn.functional.kl_div.md
index 10ef6185f37..c476ce903ce 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/functional/torch.nn.functional.kl_div.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/functional/torch.nn.functional.kl_div.md
@@ -2,7 +2,7 @@
 
 ### [torch.nn.functional.kl_div](https://pytorch.org/docs/stable/generated/torch.nn.functional.kl_div.html?highlight=kl_div#torch.nn.functional.kl_div)
 
-```
+```python
 torch.nn.functional.kl_div(input,
                target,
                size_average=None,
@@ -13,7 +13,7 @@ torch.nn.functional.kl_div(input,
 
 ### [paddle.nn.functional.kl_div](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/functional/kl_div_cn.html)
 
-```
+```python
 paddle.nn.functional.kl_div(input,
                 label,
                 reduction='mean')
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BCELoss.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BCELoss.md
index 571be10ee30..a79a175e155 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BCELoss.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BCELoss.md
@@ -34,7 +34,6 @@ torch.nn.BCELoss(weight=w, size_average=True)
 
 # Paddle 写法
 paddle.nn.BCELoss(weight=w, reduction='mean')
-
 ```
 
 size_average 为 False
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BCEWithLogitsLoss.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BCEWithLogitsLoss.md
index d0d36cd79b9..c1a5527a3e5 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BCEWithLogitsLoss.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BCEWithLogitsLoss.md
@@ -37,7 +37,6 @@ torch.nn.BCEWithLogitsLoss(weight=w, size_average=True)
 
 # Paddle 写法
 paddle.nn.BCEWithLogitsLoss(weight=w, reduction='mean')
-
 ```
 
 size_average 为 False
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BatchNorm2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BatchNorm2d.md
index 48b7a38323a..bffb8efdb2d 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BatchNorm2d.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.BatchNorm2d.md
@@ -21,7 +21,6 @@ paddle.nn.BatchNorm2D(num_features,
                       data_format='NCHW',
                       use_global_stats=True,
                       name=None)
-
 ```
 
 两者功能一致但参数不一致，部分参数名不同，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.CrossEntropyLoss.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.CrossEntropyLoss.md
index 40f8fc63a77..2b4b4514fbf 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.CrossEntropyLoss.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.CrossEntropyLoss.md
@@ -43,7 +43,6 @@ torch.nn.CrossEntropyLoss(weight=w, size_average=True)
 
 # Paddle 写法
 paddle.nn.CrossEntropyLoss(weight=w, reduction='mean')
-
 ```
 
 size_average 为 False
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.MSELoss.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.MSELoss.md
index 15582f849ce..280f7e9c9b6 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.MSELoss.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.MSELoss.md
@@ -23,6 +23,7 @@ PyTorch 相比 Paddle 支持更多其他参数，具体如下：
 
 ### 转写示例
 #### size_average
+
 ```python
 # Paddle 写法
 torch.nn.MSELoss(size_average=True)
@@ -32,17 +33,19 @@ paddle.nn.MSELoss(reduction='mean')
 ```
 
 #### size_average
+
 size_average 为 True
+
 ```python
 # PyTorch 写法
 torch.nn.MSELoss(size_average=True)
 
 # Paddle 写法
 paddle.nn.MSELoss(reduction='mean')
-
 ```
 
 size_average 为 False
+
 ```python
 # PyTorch 写法
 torch.nn.MSELoss(size_average=False)
@@ -52,7 +55,9 @@ paddle.nn.MSELoss(reduction='sum')
 ```
 
 #### reduce
+
 reduce 为 True
+
 ```python
 # PyTorch 写法
 torch.nn.MSELoss(reduce=True)
@@ -62,6 +67,7 @@ paddle.nn.MSELoss(reduction='mean')
 ```
 
 reduce 为 False
+
 ```python
 # PyTorch 写法
 torch.nn.MSELoss(reduce=False)
@@ -71,7 +77,9 @@ paddle.nn.MSELoss(reduction='none')
 ```
 
 #### reduction
+
 reduction 为'none'
+
 ```python
 # PyTorch 写法
 torch.nn.MSELoss(reduction='none')
@@ -81,6 +89,7 @@ paddle.nn.MSELoss(reduction='none')
 ```
 
 reduction 为'mean'
+
 ```python
 # PyTorch 写法
 torch.nn.MSELoss(reduction='mean')
@@ -90,6 +99,7 @@ paddle.nn.MSELoss(reduction='mean')
 ```
 
 reduction 为'sum'
+
 ```python
 # PyTorch 写法
 torch.nn.MSELoss(reduction='sum')
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.NLLLoss.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.NLLLoss.md
index 110d963bf4e..3cbfb0407ab 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.NLLLoss.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.NLLLoss.md
@@ -41,17 +41,19 @@ paddle.nn.NLLLoss(reduction='mean')
 ```
 
 #### size_average
+
 size_average 为 True
+
 ```python
 # PyTorch 写法
 torch.nn.NLLLoss(weight=w, size_average=True)
 
 # Paddle 写法
 paddle.nn.NLLLoss(weight=w, reduction='mean')
-
 ```
 
 size_average 为 False
+
 ```python
 # PyTorch 写法
 torch.nn.NLLLoss(weight=w, size_average=False)
@@ -61,7 +63,9 @@ paddle.nn.NLLLoss(weight=w, reduction='sum')
 ```
 
 #### reduce
+
 reduce 为 True
+
 ```python
 # PyTorch 写法
 torch.nn.NLLLoss(weight=w, reduce=True)
@@ -71,6 +75,7 @@ paddle.nn.NLLLoss(weight=w, reduction='mean')
 ```
 
 reduce 为 False
+
 ```python
 # PyTorch 写法
 torch.nn.NLLLoss(weight=w, reduce=False)
@@ -80,7 +85,9 @@ paddle.nn.NLLLoss(weight=w, reduction='none')
 ```
 
 #### reduction
+
 reduction 为'none'
+
 ```python
 # PyTorch 写法
 torch.nn.NLLLoss(weight=w, reduction='none')
@@ -90,6 +97,7 @@ paddle.nn.NLLLoss(weight=w, reduction='none')
 ```
 
 reduction 为'mean'
+
 ```python
 # PyTorch 写法
 torch.nn.NLLLoss(weight=w, reduction='mean')
@@ -99,6 +107,7 @@ paddle.nn.NLLLoss(weight=w, reduction='mean')
 ```
 
 reduction 为'sum'
+
 ```python
 # PyTorch 写法
 torch.nn.NLLLoss(weight=w, reduction='sum')
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.SmoothL1Loss.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.SmoothL1Loss.md
index 3393da06f6c..0fd6925b53e 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.SmoothL1Loss.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.SmoothL1Loss.md
@@ -43,7 +43,6 @@ torch.nn.SmoothL1Loss(size_average=True)
 
 # Paddle 写法
 paddle.nn.SmoothL1Loss(reduction='mean')
-
 ```
 
 size_average 为 False
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.Softmax2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.Softmax2d.md
index ec82bd2dd75..ef2be99fdab 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.Softmax2d.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/nn/torch.nn.Softmax2d.md
@@ -22,7 +22,7 @@ paddle.nn.Softmax(axis=-1)
 
 ### 转写示例
 
-```
+```python
 # PyTorch 写法
 cri = torch.nn.Softmax2d()
 cri(input)
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.acos.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.acos.md
index 0f5f14e84e8..32e723a4e0d 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.acos.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.acos.md
@@ -34,5 +34,4 @@ torch.acos(torch.tensor([0.3348, -0.5889]), out=y)
 
 # Paddle 写法
 paddle.assign(paddle.acos(paddle.to_tensor([0.3348, -0.5889])), y)
-
 ```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.scatter.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.scatter.md
index 99928ebd4ce..fb4ba91af63 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.scatter.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.scatter.md
@@ -10,7 +10,6 @@ torch.scatter(input,dim, index, src, reduce=None,out=None)
 
 ```python
 paddle.put_along_axis(arr,indices, values, axis, reduce="assign", include_self=True, broadcast=True)
-
 ```
 
 其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
@@ -31,6 +30,7 @@ paddle.put_along_axis(arr,indices, values, axis, reduce="assign", include_self=T
 ### 转写示例
 
 #### out：指定输出
+
 ```python
 # PyTorch 写法
 index = torch.tensor([[0],[1],[2]])
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.set_printoptions.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.set_printoptions.md
index 3a088fb8a72..f976612710c 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.set_printoptions.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/ops/torch.set_printoptions.md
@@ -29,7 +29,7 @@ PyTorch 相比 Paddle 支持更多其他参数，具体如下：
 
 #### profile:预设风格，设置为 `default`。
 
-```
+```python
 # PyTorch 写法
 torch.set_printoptions(profile='default')
 
@@ -39,7 +39,7 @@ paddle.set_printoptions(precision=4, threshold=1000, edgeitems=3, linewidth=80)
 
 #### profile:预设风格，设置为 `short`。
 
-```
+```python
 # PyTorch 写法
 torch.set_printoptions(profile='short')
 
@@ -49,7 +49,7 @@ paddle.set_printoptions(precision=2, threshold=1000, edgeitems=2, linewidth=80)
 
 #### profile:预设风格，设置为 `full`。
 
-```
+```python
 # PyTorch 写法
 torch.set_printoptions(profile='full')
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/utils/torch.utils.data.WeightedRandomSampler.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/utils/torch.utils.data.WeightedRandomSampler.md
index c479c746a09..b64daa8a6ef 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/utils/torch.utils.data.WeightedRandomSampler.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/utils/torch.utils.data.WeightedRandomSampler.md
@@ -2,7 +2,7 @@
 
 ### [torch.utils.data.WeightedRandomSampler](https://pytorch.org/docs/stable/data.html#torch.utils.data.WeightedRandomSampler)
 
-```
+```python
 torch.utils.data.WeightedRandomSampler(weights,
                        num_samples,
                        replacement=True,
@@ -11,7 +11,7 @@ torch.utils.data.WeightedRandomSampler(weights,
 
 ### [paddle.io.WeightedRandomSampler](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/WeightedRandomSampler_cn.html#paddle.io.WeightedRandomSampler)
 
-```
+```python
 paddle.io.WeightedRandomSampler(weights,
                 num_samples,
                 replacement=True)
diff --git a/docs/guides/model_convert/convert_from_pytorch/validate_mapping_in_api_difference.py b/docs/guides/model_convert/convert_from_pytorch/validate_mapping_in_api_difference.py
index 3e556bc9fd0..b01cbc292f6 100644
--- a/docs/guides/model_convert/convert_from_pytorch/validate_mapping_in_api_difference.py
+++ b/docs/guides/model_convert/convert_from_pytorch/validate_mapping_in_api_difference.py
@@ -112,7 +112,7 @@ def get_meta_from_diff_file(filepath):
     paddle_pattern = re.compile(
         r"^### +\[ *(?P<paddle_api>paddle.[^\]]+)\](\((?P<url>[^\)]*)\))?$"
     )
-    code_begin_pattern = re.compile(r"^```(python)?$")
+    code_begin_pattern = re.compile(r"^```python$")
     code_pattern = re.compile(r"^(?P<api_name>(paddle|torch)[^\( ]+)(.*?)$")
     code_end_pattern = re.compile(r"^```$")
 
@@ -247,10 +247,29 @@ def get_meta_from_diff_file(filepath):
     # print(state)
 
     # 允许的终止状态，解析完了 paddle_api 或者只有 torch_api
-    if state not in [ParserState.end, ParserState.wait_for_paddle_api]:
-        raise Exception(
-            f"Unexpected End State at {state} in parsing file: {filepath}, current meta: {meta_data}"
-        )
+    # 这些映射类型必须要有对应的 paddle_api
+    if mapping_type in [
+        "无参数",
+        "参数完全一致",
+        "仅参数名不一致",
+        "仅 paddle 参数更多",
+        "仅参数默认值不一致",
+        # type 2
+        "torch 参数更多",
+        # type 3
+        "返回参数类型不一致",
+        "参数不一致",
+        "参数用法不一致",
+    ]:
+        if state != ParserState.end:
+            raise Exception(
+                f"Unexpected End State at {state} in parsing file: {filepath}, current meta: {meta_data}"
+            )
+    else:
+        if state not in [ParserState.end, ParserState.wait_for_paddle_api]:
+            raise Exception(
+                f"Unexpected End State at {state} in parsing file: {filepath}, current meta: {meta_data}"
+            )
 
     return meta_data