from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-7b-hf"
)
model = PeftModelForCausalLM.from_pretrained(
    model,
    "atsuki-yamaguchi/Llama-2-7b-hf-si-30K-lapt"
)
model = model.merge_and_unload()
tokenizer = AutoTokenizer.from_pretrained(
    "meta-llama/Llama-2-7b-hf"
)

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}, 
}