Llama2 7B for Greek: 100 target vocabulary size + Align target vocabulary initialization + 2 Stage training
This model is built on top of Llama2 7B adapted for Greek using 30K target language sentences sampled from CC-100.
Model Details
- Vocabulary: This model has an additional 100 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 2 Stage strategies introduced in the paper.
Model Description
- Language: Greek
- License: Llama 2 Community License Agreement
- Fine-tuned from model: meta-llama/Llama-2-7b-hf
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
from peft import PeftModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2stage"
)
model = PeftModelForCausalLM.from_pretrained(
model,
"atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2stage"
)
model = model.merge_and_unload()
tokenizer = AutoTokenizer.from_pretrained(
"atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2stage"
)
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
- 24
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2stage
Base model
meta-llama/Llama-2-7b-hf