---
license: gemma
license_name: license
license_link: LICENSE
base_model:
- google/gemma-2-2b
pipeline_tag: translation
library_name: transformers
language:
- ar
- bn
- cs
- de
- en
- es
- fa
- fr
- he
- hi
- id
- it
- ja
- km
- ko
- lo
- ms
- my
- nl
- pl
- pt
- ru
- th
- tl
- tr
- ur
- vi
- zh
---



## Model Description
GemmaX2-28-2B-Pretrain is a language model developed through continual pretraining of Gemma2-2B 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](https://arxiv.org/pdf/2502.02481).

- **Developed by:** Xiaomi
- **Model type:** GemmaX2-28-2B-Pretrain is obtained by continually pretraining Gemma2-2B on a large amount of monolingual and parallel data. Subsequently, GemmaX2-28-2B-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.

**Note that GemmaX2-28-2B-Pretrain is NOT translation model.**


## Training Data

We collect monolingual data from [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX) and [MADLAD-400](https://huggingface.co/datasets/allenai/MADLAD-400). For parallel data, we collect all Chinese-centric and English-centric parallel datasets from the [OPUS](https://opus.nlpl.eu/) collection up to August 2024 and conduct a series of filtering processes, such as language identification, semantic duplication filtering, quality filtering, and more.


## Citation 

```bibtex
@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}, 
}
```