Skip to content

Improving the layer Description. #734

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mattdangerw merged 6 commits into from
Feb 16, 2023
Merged

Improving the layer Description. #734

Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
95b33d0
Improving the layer Description.
Neeshamraghav012 Feb 10, 2023
a656aa3
Updated the description.
Neeshamraghav012 Feb 11, 2023
f326423
White spaces removed.
Neeshamraghav012 Feb 12, 2023
de4b7bf
Update token_and_position_embedding.py
Neeshamraghav012 Feb 16, 2023
68bbd89
Update token_and_position_embedding.py
Neeshamraghav012 Feb 16, 2023
8458294
Remove trailing spaces
mattdangerw Feb 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion keras_nlp/layers/token_and_position_embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,9 @@

@keras.utils.register_keras_serializable(package="keras_nlp")
class TokenAndPositionEmbedding(keras.layers.Layer):
"""A layer which sums a token and position embedding.
"""Token and position embeddings are ways of representing words and their order in a sentence
Copy link
Member

@mattdangerw mattdangerw Feb 10, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The first line of a docstring should always be a single sentence fragment <80 characters. Let's leave this unchanged

We could add a description to the next paragraph though! Maybe....

Token and position embeddings give a dense representation of the
input tokens, and their position in the sequence respectively. This
layer create a `keras.layers.Embedding` token embedding and a
`keras_nlp.layers.PositionEmbedding` position embedding and sums
their output when called. This layer assumes that the last dimension in
the input corresponds to the sequence dimension.

so that a machine learning model like a neural network can understand them.
This layer sums a token and position embedding.
This layer assumes that the last dimension in the input corresponds
to the sequence dimension.
Expand Down