T5Gemma conversion and inference#1962
Merged
jordimas merged 15 commits intoOpenNMT:masterfrom Jan 4, 2026
Merged
Conversation
Open
Contributor
|
Thanks for your quick work on this! This looks good in my brief testing. Conversion and inference both appear to function as intended. I tested using t5gemma-s-s-prefixlm-it. The following input: [
"<start_of_turn>", "user", "\n",
"What", "▁is", "▁the", "▁capital", "▁of", "▁France", "?", "<end_of_turn>", "\n",
"<start_of_turn>", "model", "\n"
]Correctly produces this output: [
"The", "▁capital", "▁of", "▁France", "▁is", "▁**", "Paris", "**.", "▁", "\n"
] |
a2d8a4v
pushed a commit
to a2d8a4v/CTranslate2
that referenced
this pull request
Jan 13, 2026
See OpenNMT#1946 Changes: - Support for T5Gemma family models - Extract qk_norm logic to its own method - Add support for rotary embeddings and pre and post layers in encoder - Support for different types of cross attention and unit tests
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
See #1946
Python wheels are available to test here:
https://github.com/OpenNMT/CTranslate2/actions/runs/20646214823#artifacts
Changes: