omercelik/
gemmax2-9b

LLM-based translation model

102 4 weeks ago

1 Tag

Readme

Model Description

GemmaX2-28-9B-v0.1 is an LLM-based translation model. It has been fintuned on GemmaX2-28-9B-Pretrain, which is a language model developed through continual pretraining of Gemma2-9B using a mix of 56 billion tokens from both monolingual and parallel data across 28 different languages. Please find more details in our paper: Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study.

  • Developed by: Xiaomi
  • Model type: GemmaX2-28-9B-Pretrain is obtained by continually pretraining Gemma2-9B on a large amount of monolingual and parallel data. Subsequently, GemmaX2-28-9B-v0.1 is derived through supervised finetuning on a small set of high-quality translation instruction data.
  • Languages: Arabic, Bengali, Czech, German, English, Spanish, Persian, French, Hebrew, Hindi, Indonesian, Italian, Japanese, Khmer, Korean, Lao, Malay, Burmese, Dutch, Polish, Portuguese, Russian, Thai, Tagalog, Turkish, Urdu, Vietnamese, Chinese.

Model Performance

Experimental Result

Run the model

ollama run omercelik/gemmax2-9b "Translate this from Chinese to English:\nChinese: 我爱机器翻译\nEnglish:"

I love machine translation

Citation

@misc{cui2025multilingualmachinetranslationopen,
      title={Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study}, 
      author={Menglong Cui and Pengzhi Gao and Wei Liu and Jian Luan and Bin Wang},
      year={2025},
      eprint={2502.02481},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.02481}, 
}

Limitations

GemmaX2-28-9B-v0.1 only supports the 28 languages listed above and does not guarantee strong translation performance for other languages. We will continue to enhance the translation performance of GemmaX2-28-9B, and future models will be released in due course.