Edit model card

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

This model is built on top of Llama3 8B adapted for Telugu 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 Random 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: Telugu
  • License: Llama 3 Community License Agreement
  • Fine-tuned from model: meta-llama/Meta-Llama-3-8B

Model Sources

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

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}, 
}
Downloads last month
5
Safetensors
Model size
8.56B params
Tensor type
F32
·
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for atsuki-yamaguchi/Llama-3-8B-te-30K-500-rand

Finetuned
this model