|
--- |
|
license: other |
|
license_name: license |
|
license_link: LICENSE |
|
--- |
|
|
|
# Model Card for GemmaX2-28 |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
GemmaX2-28-2B-Pretrain is a language model that results from continual pretraining of Gemma2-2B on a mix of 56 billion tokens of monolingual and parallel data in 28 different 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. |
|
|
|
GemmaX2-28-2B-v0.1 is the first model in the series. Compared to the current open-source state-of-the-art (SOTA) models, it achieves optimal translation performance across 28 languages, even reaching performance comparable to GPT-4 and Google Translate, indicating it has achieved translation capabilities on par with industry standards. |
|
|
|
- **Developed by:** Xiaomi |
|
- **Model type:** A 2B parameter model base on Gemma2, we obtained GemmaX2-28-9B-Pretrain by continuing pre-training on a large amount of monolingual and parallel data. Afterward, GemmaX2-28-9B-v0.1 was derived through supervised fine-tuning on a small set of high-quality instruction data. |
|
- **Language(s) (NLP):** 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. |
|
- **License:** gemma |
|
|
|
### Model Source |
|
|
|
- paper: coming soon. |
|
|
|
### Model Performance |
|
|
|
 |
|
|
|
## Limitations |
|
|
|
GemmaX2-28-2B-v0.1 supports only the 28 most commonly used languages and does not guarantee powerful translation performance for other languages. Additionally, we will continue to improve GemmaX2-28-9B's translation performance, and future models will be release in due course. |
|
|
|
|
|
|
|
## Run the model |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model_id = "ModelMagician/GemmaX2-28-9B-v0.1" |
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
|
model = AutoModelForCausalLM.from_pretrained(model_id) |
|
|
|
text = "Translate this from Chinese to English:\nChinese: 我爱机器翻译\nEnglish:" |
|
inputs = tokenizer(text, return_tensors="pt") |
|
|
|
outputs = model.generate(**inputs, max_new_tokens=50) |
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
|
|
### Training Data |
|
|
|
We collected monolingual data from [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX) and [MADLAD-400](https://huggingface.co/datasets/allenai/MADLAD-400). For parallel data, we collected all Chinese-centric and English-centric parallel dataset from the [OPUS](https://opus.nlpl.eu/) collection up to Auguest 2024 and underwent a series of filtering processes, such as language detection, semantic duplication filtering, quality filtering, and more. |
|
|
|
## Citation |
|
|
|
```bibtex |
|
@misc{gemmax2, |
|
title = {Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study}, |
|
url = {}, |
|
author = {XiaoMi Team}, |
|
month = {October}, |
|
year = {2024} |
|
} |
|
``` |
