license: apache-2.0
datasets:
- HuggingFaceFW/fineweb
- HuggingFaceFW/fineweb-2
language:
- en
- uk
- zh
- hi
- ko
- ar
- th
- el
tags:
- pixel
- mae
- vit
- tokenization-free
MPIXEL
MPIXEL, introduced in Scaling Multilingual Pretraining of Pixel Language Models, is a family of multilingual pixel language models, which operate on visually rendered text. Our main models, mpixel-base (86M parameters) and mpixel-large (307M parameters), are pretrained on sixteen languages that span ten writing systems. MPIXEL uses adaptive rendering: it renders text as grapheme bigrams by default, Chinese, Japanese and Korean text one character per patch, and Arabic and Hebrew text word by word.
This model is mpixel-8l, which is pretrained on eight languages: English, Hindi, Chinese, Ukrainian, Korean, Thai, Modern Greek and Standard Arabic.
Basic usage
To use our models, please first install our mpixel package. Here is an example of loading a pretrained model and encoding input text:
from transformers import AutoModel
import mpixel.models.auto_register # registers MPIXEL with the Auto classes
from mpixel.processing import MPIXELProcessor
processor = MPIXELProcessor.from_pretrained("Team-PIXEL/mpixel-8s")
model = AutoModel.from_pretrained("Team-PIXEL/mpixel-8s")
inputs = processor(["Hello world!", "The quick brown fox jumps over the lazy dog."])
outputs = model(**inputs)
print(outputs.last_hidden_state.shape) # torch.Size([2, 513, 768])
For further information, please take a look at our repository: https://github.com/ilkerkesen/mpixel.
Citation
If you find MPIXEL beneficial for your research, please cite it,
@misc{kesen2026scalingmultilingualpretrainingpixel,
title={Scaling Multilingual Pretraining of Pixel Language Models},
author={Ilker Kesen and Jenny Kunz and Kasra Malihi and Desmond Elliott},
year={2026},
eprint={2610.29681},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2610.29681},
}