10BC0 Gemma 3 support (text only) by jordimas · Pull Request #1936 · OpenNMT/CTranslate2 · GitHub
[go: up one dir, main page]
Skip to content

Gemma 3 support (text only) #1936

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
Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Gemma 3 support (text only) #1936

wants to merge 1 commit into from
+286 −1

Conversation

@jordimas
Copy link
Collaborator
@jordimas jordimas commented Nov 23, 2025 •
edited
Loading

Gemma 3 text only model support

Pending:

  • More testing with some real use cases
  • Test with all model family variant

In case you want to test it, wheels are built here:

https://github.com/OpenNMT/CTranslate2/actions/runs/19616197187#artifacts

@vince62s
Copy link
Member
vince62s commented Nov 23, 2025

while you implement q/k_norm just in case you want to implement Hunyuan-MT-7B (probably the best MT model so far) they do q/k_norm AFTER rotary instead of before.
FYI, Eole implementation here: https://github.com/eole-nlp/eole/blob/main/eole/modules/multi_headed_attn.py#L259-L274

@jordimas jordimas changed the title Gemma 3 only support Gemma 3 support (text only) Nov 23, 2025
@jordimas jordimas mentioned this pull request Nov 23, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@jordimas @vince62s
0