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.

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

Jump to bottom

MixtralSparseMoeBlock: add gate jitter #29865

Merged
merged 1 commit into from
Mar 27, 2024
Merged

MixtralSparseMoeBlock: add gate jitter #29865

merged 1 commit into from
Mar 27, 2024

Conversation

lorenzoverardo
Copy link
Contributor

What does this PR do?

This PR adds gate jitter to MixtralSparseMoeBlock's input data before passing it through the MoE layer, if turned on.
Fixes #29429.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

ArthurZucker
ArthurZucker reviewed Mar 26, 2024
View reviewed changes
Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

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

Thanks!

src/transformers/models/mixtral/configuration_mixtral.py Outdated Show resolved Hide resolved
src/transformers/models/mixtral/configuration_mixtral.py Outdated Show resolved Hide resolved
src/transformers/models/mixtral/modeling_mixtral.py Outdated Show resolved Hide resolved
ArthurZucker
ArthurZucker approved these changes Mar 27, 2024
View reviewed changes
Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

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

Last nit and good to go!

tests/models/mixtral/test_modeling_mixtral.py Outdated Show resolved Hide resolved
@lorenzoverardo
MixtralSparseMoeBlock: add gate jitter
09a2adf 
This commit adds gate jitter to MixtralSparseMoeBlock's input data
before passing it through the MoE layer, if turned on.
@ArthurZucker ArthurZucker merged commit a25037b into huggingface:main Mar 27, 2024
18 checks passed
@ArthurZucker
Copy link
Collaborator

Thanks for the contribution!

@ArthurZucker
Copy link
Collaborator

FYI @younesbelkada

@lorenzoverardo lorenzoverardo deleted the feat/add-jitter branch March 27, 2024 15:30
@HuggingFaceDocBuilderDev
Copy link

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

itazap pushed a commit that referenced this pull request May 14, 2024
@lorenzoverardo
MixtralSparseMoeBlock: add gate jitter (#29865)
7142e23 
This commit adds gate jitter to MixtralSparseMoeBlock's input data
before passing it through the MoE layer, if turned on.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ArthurZucker ArthurZucker ArthurZucker approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Gate jitter is missing from Sparse MoE routing implementation
3 participants
@lorenzoverardo @ArthurZucker @HuggingFaceDocBuilderDev