[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

neural_network/sliding_window_attention.py

@@ -1,7 +1,7 @@
 """
  - - - - - -- - - - - - - - - - - - - - - - - - - - - - -
 Name - - sliding_window_attention.py
-Goal - - Implement a neural network architecture using sliding 
+Goal - - Implement a neural network architecture using sliding
         window attention for sequence modeling tasks.
 Detail: Total 5 layers neural network
         * Input layer
@@ -12,11 +12,11 @@
 Github: [email protected]
 Date: 2024.10.20
 References:
-    1. Choromanska, A., et al. (2020). "On the Importance of 
-       Initialization and Momentum in Deep Learning." *Proceedings 
+    1. Choromanska, A., et al. (2020). "On the Importance of
+       Initialization and Momentum in Deep Learning." *Proceedings
        of the 37th International Conference on Machine Learning*.
-    2. Dai, Z., et al. (2020). "Transformers are RNNs: Fast 
-       Autoregressive Transformers with Linear Attention." 
+    2. Dai, Z., et al. (2020). "Transformers are RNNs: Fast
+       Autoregressive Transformers with Linear Attention."
        *arXiv preprint arXiv:2006.16236*.
     3. [Attention Mechanisms in Neural Networks](https://en.wikipedia.org/wiki/Attention_(machine_learning))
  - - - - - -- - - - - - - - - - - - - - - - - - - - - - -
@@ -28,7 +28,7 @@
 class SlidingWindowAttention:
     """Sliding Window Attention Module.
 
-    This class implements a sliding window attention mechanism where 
+    This class implements a sliding window attention mechanism where
     the model attends to a fixed-size window of context around each token.
 
     Attributes:
@@ -54,13 +54,13 @@ def forward(self, input_tensor: np.ndarray) -> np.ndarray:
         Forward pass for the sliding window attention.
 
         Args:
-            input_tensor (np.ndarray): Input tensor of shape (batch_size, 
+            input_tensor (np.ndarray): Input tensor of shape (batch_size,
                                        seq_length, embed_dim).
 
         Returns:
             np.ndarray: Output tensor of shape (batch_size, seq_length, embed_dim).
 
-        >>> x = np.random.randn(2, 10, 4)  # Batch size 2, sequence 
+        >>> x = np.random.randn(2, 10, 4)  # Batch size 2, sequence
         >>> attention = SlidingWindowAttention(embed_dim=4, window_size=3)
         >>> output = attention.forward(x)
         >>> output.shape
@@ -95,7 +95,7 @@ def forward(self, input_tensor: np.ndarray) -> np.ndarray:
 
     # usage
     rng = np.random.default_rng()
-    x = rng.standard_normal((2, 10, 4))  # Batch size 2, 
+    x = rng.standard_normal((2, 10, 4))  # Batch size 2,
     attention = SlidingWindowAttention(embed_dim=4, window_size=3)
     output = attention.forward(x)
     print(output)