Llama-2-7b-hf-el-30K-align-2x2ls-512 – AI Model by atsuki-yamaguchi | AlphaNeural AI

You can deploy this model and start earning money today!

atsuki-yamaguchi/
Llama-2-7b-hf-el-30K-align-2x2ls-512

like

0

text-generation

meta-llama/Llama-2-7b-hf

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

Llama2 7B for Greek: 100 target vocabulary size + Align target vocabulary initialization + 2x2LS/512 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 2x2LS/512 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

How to Get Started with the Model

Use the code below to get started with the model.

python

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2x2ls-512"
)
tokenizer = AutoTokenizer.from_pretrained(
    "atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2x2ls-512"
)

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}, 
}