Export for Phi4-mini #36780
Merged
Export for Phi4-mini #36780
Conversation
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
Contributor
|
Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. When it is ready for review, please click the |
qubvel
added
torch export
Contributor
|
run-slow: phi3 |
Contributor
|
This comment contains run-slow, running the specified jobs: This comment contains run-slow, running the specified jobs: models: ['models/phi3'] |
Contributor
Author
|
run-slow: phi3 |
Contributor
Author
|
cc: @tugsbayasgalan |
Collaborator
FYI: this trigger by comment is only reserved for some |
Collaborator
|
run-slow: phi3 |
Contributor
|
This comment contains run-slow, running the specified jobs: This comment contains run-slow, running the specified jobs: models: ['models/phi3'] |
zucchini-nlp
pushed a commit
to zucchini-nlp/transformers
that referenced
this pull request
May 14, 2025
* Export for Phi4-mini * Update tests/models/phi3/test_modeling_phi3.py --------- Co-authored-by: Guang Yang <guangyang@fb.com> Co-authored-by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>
soghomon-b
pushed a commit
to soghomon-b/transformers
that referenced
this pull request
Aug 24, 2025
* Export for Phi4-mini * Update tests/models/phi3/test_modeling_phi3.py --------- Co-authored-by: Guang Yang <guangyang@fb.com> Co-authored-by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>
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Outdated suggestions cannot be applied.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?
As titled. Add support for Phi3-mini and Phi4-mini as they are sharing the same modeling code. It's requiring additional configure (rope_type = "default") to make it exportable, otherwise we will have to rewrite the modeling code, specifically, specialize or get rid of the control flow in
_longrope_frequency_update.Before submitting
Pull Request section?
to it if that's the case. Phi3 is ExecuTorch compatible #33838
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 @amyeroberts @qubvel