atsuki-yamaguchi/Llama-3-8B-si-30K-500-align

Llama3 8B for Sinhala: 500 target vocabulary size + Align target vocabulary initialization + 2x2LS/MTP/512 training

This model is built on top of Llama3 8B adapted for Sinhala using 30K target language sentences sampled from CC-100.

Model Details

• Vocabulary: This model has an additional 500 target vocabulary.
• Target vocabulary initialization: The target weights of the embedding and LM head were initialized using Align initialization.
• Training: This model was additionally pre-trained on 30K target language sentences sampled from CC-100. The training was conducted with the 2x2LS/MTP/512 strategies introduced in the paper.

Model Description

• Language: Sinhala
• License: Llama 3 Community License Agreement
• Fine-tuned from model: meta-llama/Meta-Llama-3-8B

Model Sources

• Repository: https://github.com/gucci-j/lowres-cve
• Paper: https://arxiv.org/abs/2406.11477

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-3-8B-si-30K-500-align"
)
tokenizer = AutoTokenizer.from_pretrained(
    "atsuki-yamaguchi/Llama-3-8B-si-30K-500-align"
)

Citation

@article{yamaguchi-etal-2024-effectively,
    title={How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?}, 
    author={Atsuki Yamaguchi and Aline Villavicencio and Nikolaos Aletras},
    year={2024},
    journal={ArXiv},
    year={2024},
    volume={abs/2406.11477},
    url={https://arxiv.org/abs/2406.11477}, 
}