metadata

license: llama3.1
datasets:
  - allenai/MADLAD-400
language:
  - my
base_model:
  - meta-llama/Llama-3.1-8B-Instruct
library_name: transformers

Llama 3.1 8B Instruct for Burmese: Vocabulary expansion

This model is built on top of Llama 3.1 8B Instruct adapted for Burmese using 500M target language tokens sampled from MADLAD-400. It has an additional target vocabulary of 10K.

Model Details

Vocabulary: This model has an additional target vocabulary of 10K.
Target vocabulary initialization: The target weights of the embedding and LM head were initialized using mean initialization.
Training: This model was continually pre-trained on 500M target language tokens sampled from MADLAD-400.

Model Description

Language: Burmese
License: Llama 3.1 Community License Agreement
Fine-tuned from model: meta-llama/Llama-3.1-8B-Instruct

Model Sources

Repository: https://github.com/gucci-j/chat-cve
Paper: https://arxiv.org/abs/2412.11704

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "atsuki-yamaguchi/Llama-3.1-8B-Instruct-my-madlad-mean-tuned"
)
tokenizer = AutoTokenizer.from_pretrained(
    "atsuki-yamaguchi/Llama-3.1-8B-Instruct-my-madlad-mean-tuned"
)

Citation

@misc{yamaguchi2024vocabularyexpansionchatmodels,
      title={{ElChat}: Adapting Chat Language Models Using Only Target Unlabeled Language Data}, 
      author={Atsuki Yamaguchi and Terufumi Morishita and Aline Villavicencio and Nikolaos Aletras},
      year={2024},
      eprint={2412.11704},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.11704},
}