Skip to content

WIP : First implementation of sliding window local sparse attention.#951

Open
natsegal wants to merge 13 commits into
OpenNMT:masterfrom
natsegal:sparse_attention
Open

WIP : First implementation of sliding window local sparse attention.#951
natsegal wants to merge 13 commits into
OpenNMT:masterfrom
natsegal:sparse_attention

Conversation

@natsegal

Copy link
Copy Markdown

No description provided.

@guillaumekln guillaumekln left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

The code is clear and you added comments + tests so this looks great to me. I have few comments:

Comment thread opennmt/layers/transformer.py Outdated
Comment thread opennmt/layers/transformer.py Outdated
Comment thread opennmt/layers/transformer.py Outdated
Comment thread opennmt/layers/transformer.py Outdated
Comment thread opennmt/layers/transformer.py Outdated
Comment thread opennmt/tests/transformer_test.py Outdated
Comment thread opennmt/tests/transformer_test.py Outdated
Comment thread opennmt/layers/transformer.py
Comment thread opennmt/layers/transformer.py Outdated
Comment thread opennmt/layers/transformer.py
Comment thread opennmt/layers/transformer.py Outdated
Comment thread opennmt/layers/transformer.py
Comment thread opennmt/layers/transformer.py
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants