Task
Translation
M
xiaomi-research/MiLMMT-46-4B-v0.1
Translation·xiaomi-research· 263· 2
transformers
gemma
Translation
4.3B params
arxiv:2602.11961base_model:xiaomi-research/MiLMMT-46-4B-Pretrainbase_model:finetune:xiaomi-research/MiLMMT-46-4B-Pretrainlicense:gemmaregion:us
MiLMMT-46-4B-v0.1 is an LLM-based translation model. It has been fintuned on MiLMMT-46-4B-Pretrain, which is a language model developed through continual pretraining of Gemma3-4B using a mix of 143 billion tokens from both monolingual and parallel data across 46 different languages. Please find more details in our paper: Scaling Model and Data for Multilingual Machine Translation with Open Large L
# pull & run locally
pip install mlforge-sdk && mlforge pull xiaomi-research/MiLMMT-46-4B-v0.1
pip install mlforge-sdk && mlforge pull xiaomi-research/MiLMMT-46-4B-v0.1
Model details
Provider
xiaomi-research
Framework
transformers
Parameters
4.3B
Size
9.3 GB
License
gemma
Downloads
263
Likes
2
Paper
arXiv:2602.11961
Updated
2026-02-13
About xiaomi-research/MiLMMT-46-4B-v0.1
MiLMMT-46-4B-v0.1 is an LLM-based translation model. It has been fintuned on MiLMMT-46-4B-Pretrain, which is a language model developed through continual pretraining of Gemma3-4B using a mix of 143 billion tokens from both monolingual and parallel data across 46 different languages. Please find more details in our paper: Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models.