Improve language tag

#1
by lbourdois - opened

Hi! As the model is multilingual, this is a PR to add other languages than English to the language tag to improve the referencing. Note that 29 languages are announced in the README, but only 13 are explicitly listed. I was therefore only able to add these 13 languages.

LLM Group, Institute for Advanced Algorithms Research, Shanghai org

Hi there,

Thank you very much for taking the time to submit this PR and for improving our language tags! We really appreciate your effort.

At the moment, xVerify has been trained and validated primarily on Chinese and English data, which is why our README only explicitly lists those two languages. Although the underlying model may support additional languages, we haven’t yet assessed its performance or stability beyond zh/en. If you’d like to extend the tags to cover more languages, could you please run some basic evaluations or stability tests on those new language settings and share your findings? Once we’ve confirmed that the model behaves reliably in those languages, we’ll be happy to merge the expanded list.

Thanks again for your contribution, and we look forward to your results!

Ah my bad, my loop referencing all the Qwen-2.5 models to be tagged didn't take into account the case of finetuning on a specific language
Sorry for the inconvenience

LLM Group, Institute for Advanced Algorithms Research, Shanghai org

Hi again,

No worries at all—thank you for the clarification! We really appreciate your attention to detail and your contributions. If you have any further updates or need assistance with testing, please don’t hesitate to let us know.

Thanks again!

Ready to merge
This branch is ready to get merged automatically.
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment