Skip to content
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.

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

Fetching relevants position embeddings instead of all. May increase s… #2

Merged
merged 4 commits into from Feb 4, 2022

Conversation

hammad26
Copy link
Contributor

Hi
Relevant position embeddings were only the first one and last one, but all were being calculated. I updated the code to focus only on relevant position embeddings (first and last one). I am hoping that it will improve speed and will also save some memory as well.

@hammad26
Copy link
Contributor Author

hammad26 commented Feb 3, 2022

Hi
Decoder part has some serious issue with imports. Corrected the imports and also, beam_size argument was commented in decoder but was being used at the time of model creation. Fixed that as well.

@SuperSupermoon
Copy link
Owner

Thanks for correcting the typo.

@SuperSupermoon SuperSupermoon reopened this Feb 4, 2022
@SuperSupermoon SuperSupermoon merged commit 9c258c7 into SuperSupermoon:master Feb 4, 2022
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.

None yet

2 participants