a few more comments

Author: drisspg

beginner_source/scaled_dot_product_attention_tutorial.py

@@ -1,5 +1,5 @@
 """
-An overview of torch.nn.functional.scaled_dot_product_attention
+Create High-Performance Transformer Variations with Scaled Dot Product Attention
 ===============================================================
 
 """
@@ -14,8 +14,7 @@
 # function is named ``torch.nn.functional.scaled_dot_product_attention``.
 # There is some extensive documentation on the function in the `PyTorch
 # documentation <https://pytorch.org/docs/master/generated/torch.nn.functional.scaled_dot_product_attention.html#torch.nn.functional.scaled_dot_product_attention>`__.
-# This function has already been incorporated into torch.nn.MHA
-# (Multi-Head Attention) and ``torch.nn.TransformerEncoderLayer``.
+# This function has already been incorporated into torch.nn.MultiheadAttention# (Multi-Head Attention) and ``torch.nn.TransformerEncoderLayer``.
 #
 # Overview
 # ~~~~~~~
@@ -57,8 +56,8 @@
 # implementations, the user can also explicitly control the dispatch via
 # the use of a context manager. This context manager allows users to
 # explicitly disable certain implementations. If a user wants to ensure
-# the function is indeed using the fasted implementation for their
-# specific inputs the context manager can be used to sweep through
+# the function is indeed using the fastest implementation for their
+# specific inputs, the context manager can be used to sweep through
 # measuring performance.
 #
 

index.rst

@@ -525,7 +525,7 @@ What's new in PyTorch tutorials?
    :tags: Model-Optimization
 
 .. customcarditem::
-   :header: (beta) An overview of torch.nn.functional.scaled_dot_product_attention
+   :header: (beta) Create High-Performance Transformer Variations with Scaled Dot Product Attention
    :card_description: This tutorial explores the new torch.nn.functional.scaled_dot_product_attention and how it can be used to construct Transformer components.
    :image: _static/img/thumbnails/cropped/pytorch-logo.png
    :link: beginner/scaled_dot_product_attention_tutorial.html