Skip to content

Conversation

@akoumpa
Copy link
Contributor

@akoumpa akoumpa commented Dec 17, 2025

What does this PR do ?

  • add configs from devstral-small-2-2512
  • backports devstral's tokenizer from v5 to v4
  • refactors tokenization
  • update ministral registration to use transformers' API

Note: this PR classifies devstral as an LLM. VLM support will be added once we upgrade to transformers v5 (currently in RC stage).

Changelog

  • Add specific line by line info of high level changes in this PR.

Before your PR is "Ready for review"

Pre checks:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you add or update any necessary documentation?

If you haven't finished some of the above items you can still open "Draft" PR.

Additional Information

  • Related to # (issue)
Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
@copy-pr-bot
Copy link

copy-pr-bot bot commented Dec 17, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@akoumpa
Copy link
Contributor Author

akoumpa commented Dec 17, 2025

/ok to test 79c3c75

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
@akoumpa
Copy link
Contributor Author

akoumpa commented Dec 17, 2025

/ok to test 63d230b

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
@akoumpa
Copy link
Contributor Author

akoumpa commented Dec 17, 2025

/ok to test 8fdb419

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
@akoumpa
Copy link
Contributor Author

akoumpa commented Dec 18, 2025

/ok to test ee70e99

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
@akoumpa
Copy link
Contributor Author

akoumpa commented Dec 18, 2025

/ok to test 74e8e3c

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

2 participants