Update Mixtral modeling#28403
Closed
imoneoi wants to merge 1 commit into
Closed
Conversation
The [Mixtral technical report](https://arxiv.org/pdf/2401.04088.pdf) was published recently, showing that Mixtral routing weights are calculated in the top-K before softmax order.
5 tasks
|
It worries me a little bit that Mistral has different implementations for this specific process in the model. They submitted a PR to vLLM which is aligned with the current Huggingface implementation: |
Collaborator
|
Yep, we tried to follow this instead of the paper as they shared that code. Thanks for submitting a pr anyways 🤗 |
Contributor
|
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread. Please note that issues that do not follow the contributing guidelines are likely to be ignored. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
The Mixtral technical report was published recently, showing that Mixtral routing weights are calculated in the top-K before softmax order.
This PR updates the Mixtral model implementation accordingly.
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
@ArthurZucker @younesbelkada