feat: add Ministral3 embedding distillation recipe#3058
Merged
rnyak merged 15 commits intoJul 15, 2026
Conversation
Add EmbeddingDistillRecipe with RetrieverStudentWithProjection / RetrieverTeacherEmbeddingEncoder, distillation losses (cosine / MSE / InfoNCE-distill), intermediate-layer distillation, cross-tokenizer cached-teacher support, bi-encoder distill collator, example config, and unit tests. Signed-off-by: Vinay Raman <viraman@nvidia.com>
Collaborator
|
/claude review |
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
jiaruic09
reviewed
Jul 13, 2026
rnyak
reviewed
Jul 13, 2026
Signed-off-by: Vinay Raman <viraman@nvidia.com>
Signed-off-by: Vinay Raman <viraman@nvidia.com>
Signed-off-by: Vinay Raman <viraman@nvidia.com>
Collaborator
|
/ok to test fbcddc8 |
Collaborator
|
/ok to test 25e219e |
Contributor
|
/ok to test 500b983 |
Contributor
|
/ok to test 1db9e76 |
3 tasks
rnyak
approved these changes
Jul 15, 2026
adil-a
approved these changes
Jul 15, 2026
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
7 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 ?
Support for knowledge distillation (KD) of embedding/retriever models
Changelog
Before your PR is "Ready for review"
Pre checks:
If you haven't finished some of the above items you can still open "Draft" PR.
Additional Information