@inproceedings{dima-etal-2024-roqllama,
title = "{R}o{QL}lama: A Lightweight {R}omanian Adapted Language Model",
author = "Dima, George-Andrei and
Avram, Andrei-Marius and
Craciun, Cristian-George and
Cercel, Dumitru-Clementin",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.261",
pages = "4531--4541",
abstract = "The remarkable achievements obtained by open-source large language models (LLMs) in recent years have predominantly been concentrated on tasks involving the English language. In this paper, we aim to advance the performance of Llama2 models on Romanian tasks. We tackle the problem of reduced computing resources by using QLoRA for training. We release RoQLlama-7b, a quantized LLM, which shows equal or improved results compared to its full-sized counterpart when tested on seven Romanian downstream tasks in the zero-shot setup. Also, it consistently achieves higher average scores across all few-shot prompts. Additionally, we introduce a novel Romanian dataset, namely RoMedQA, which contains single-choice medical questions in Romanian.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dima-etal-2024-roqllama">
<titleInfo>
<title>RoQLlama: A Lightweight Romanian Adapted Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">George-Andrei</namePart>
<namePart type="family">Dima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei-Marius</namePart>
<namePart type="family">Avram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristian-George</namePart>
<namePart type="family">Craciun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dumitru-Clementin</namePart>
<namePart type="family">Cercel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The remarkable achievements obtained by open-source large language models (LLMs) in recent years have predominantly been concentrated on tasks involving the English language. In this paper, we aim to advance the performance of Llama2 models on Romanian tasks. We tackle the problem of reduced computing resources by using QLoRA for training. We release RoQLlama-7b, a quantized LLM, which shows equal or improved results compared to its full-sized counterpart when tested on seven Romanian downstream tasks in the zero-shot setup. Also, it consistently achieves higher average scores across all few-shot prompts. Additionally, we introduce a novel Romanian dataset, namely RoMedQA, which contains single-choice medical questions in Romanian.</abstract>
<identifier type="citekey">dima-etal-2024-roqllama</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.261</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>4531</start>
<end>4541</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RoQLlama: A Lightweight Romanian Adapted Language Model
%A Dima, George-Andrei
%A Avram, Andrei-Marius
%A Craciun, Cristian-George
%A Cercel, Dumitru-Clementin
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F dima-etal-2024-roqllama
%X The remarkable achievements obtained by open-source large language models (LLMs) in recent years have predominantly been concentrated on tasks involving the English language. In this paper, we aim to advance the performance of Llama2 models on Romanian tasks. We tackle the problem of reduced computing resources by using QLoRA for training. We release RoQLlama-7b, a quantized LLM, which shows equal or improved results compared to its full-sized counterpart when tested on seven Romanian downstream tasks in the zero-shot setup. Also, it consistently achieves higher average scores across all few-shot prompts. Additionally, we introduce a novel Romanian dataset, namely RoMedQA, which contains single-choice medical questions in Romanian.
%U https://aclanthology.org/2024.findings-emnlp.261
%P 4531-4541
Markdown (Informal)
[RoQLlama: A Lightweight Romanian Adapted Language Model](https://aclanthology.org/2024.findings-emnlp.261) (Dima et al., Findings 2024)
ACL
- George-Andrei Dima, Andrei-Marius Avram, Cristian-George Craciun, and Dumitru-Clementin Cercel. 2024. RoQLlama: A Lightweight Romanian Adapted Language Model. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 4531–4541, Miami, Florida, USA. Association for Computational Linguistics.