metadata
library_name: transformers
pipeline_tag: text-generation
language:
- multilingual
tags:
- generation
- question answering
- instruction tuning
datasets:
- MBZUAI/Bactrian-X
license: cc-by-nc-4.0
Model Description
This HF repository hosts instruction fine-tuned multilingual BLOOM model using the parallel instruction dataset called Bactrain-X in 52 languages. We progressively add a language during instruction fine-tuning at each time, and train 52 models in total. Then, we evaluate those models in three multilingual benchmarks.
Please refer to our paper for more details.
- Base model: BLOOM 7B1
- Instruction languages: English, Chinese, Afrikaans, Arabic, Azerbaijani, Bengali, Czech, German, Spanish, Estonian, Farsi, Finnish, French
- Instruction language codes: en, zh, af, ar, az, bn, cs, de, es, et, fa, fi, fr
- Training method: full-parameter fine-tuning.
Usage
The model checkpoint should be loaded using transformers library.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-13")
model = AutoModelForCausalLM.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-13")
Citation
@inproceedings{ji2025lucky52,
title={How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM},
author={Shaoxiong Ji and Pinzhen Chen},
year={2025},
booktitle={Proceedings of COLING},
url={https://arxiv.org/abs/2404.04850},
}