Convert_tokenizer support #3699
Merged
+199
−12
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
mzegla
reviewed
Oct 14, 2025
src/pull_module/optimum_export.cpp
Outdated
| output = exec_cmd(this->CONVERT_TOKENIZER_CHECK_COMMAND, retCode); | ||
| if (retCode != 0) { | ||
| SPDLOG_DEBUG("Command output {}", output); | ||
| SPDLOG_ERROR("Trying to pull {} from HuggingFace but missing convert_tokenizer. Use the ovms package with convert_tokenizer.", this->sourceModel); |
There was a problem hiding this comment.
Not sure if this error log is readable - I mean next step is not very clear to me. Is convert_tokenizer a parameter?
mzegla
approved these changes
Oct 16, 2025
dtrawins
reviewed
Oct 16, 2025
| // clang-format off | ||
| oss << this->CONVERT_TOKENIZER_EXPORT_COMMAND; | ||
| oss << this->sourceModel; | ||
| oss << " --with-detokenizer -o "; |
There was a problem hiding this comment.
in some pipelines there is no detokenizer. was it tested?
|
Missing openvino_tokenizers.cli as convert_tokenizer on windows. |
|
Need to test demos with this. |
dtrawins
approved these changes
Oct 20, 2025
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Outdated suggestions cannot be applied.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.
🛠 Summary
Check if openvino_detokenizer.xml exists after export.
If it doesn't exist call convert_tokenizer for the model.
🧪 Checklist
``