hugpadhugpad

xiaomi-research / MiLMMT-46-12B-Pretrain

Vision12B192Updated Feb 13, 2026
Hugging Face

Downloads

19

Likes

2

Last updated

Feb 13, 2026

License

gemma

MiLMMT-46-12B-Pretrain is a language model developed through continual pretraining of Gemma3-12B 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 Multiling…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • gemma3
  • image-text-to-text
  • conversational

Technical specifications

Parameters12B
Librarytransformers
LanguagesNot available
Base modelgoogle/gemma-3-12b-pt
Licensegemma