<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tahir-etal-2024-jora">
    <titleInfo>
        <title>JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Anique</namePart>
        <namePart type="family">Tahir</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lu</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yixin</namePart>
            <namePart type="family">Cao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Feng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Deyi</namePart>
            <namePart type="family">Xiong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The scaling of Large Language Models (LLMs) for retrieval-based tasks, particularly in Retrieval Augmented Generation (RAG), faces significant memory constraints, especially when fine-tuning extensive prompt sequences. Current open-source libraries support full-model inference and fine-tuning across multiple GPUs but fall short of accommodating the efficient parameter distribution required for retrieved context. Addressing this gap, we introduce a novel framework for PEFT-compatible fine-tuning of GPT models, leveraging distributed training. Our framework uniquely utilizes JAX’s just-in-time (JIT) compilation and tensor-sharding for efficient resource management, thereby enabling accelerated fine-tuning with reduced memory requirements. This advancement significantly improves the scalability and feasibility of fine-tuning LLMs for complex RAG applications, even on systems with limited GPU resources. Our experiments show more than 12x improvement in runtime compared to Hugging Face/DeepSpeed implementation with four GPUs while consuming less than half the VRAM per GPU.</abstract>
    <identifier type="citekey">tahir-etal-2024-jora</identifier>
    <identifier type="doi">10.18653/v1/2024.acl-demos.15</identifier>
    <location>
        <url>https://aclanthology.org/2024.acl-demos.15</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>152</start>
            <end>159</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning
%A Tahir, Anique
%A Cheng, Lu
%A Liu, Huan
%Y Cao, Yixin
%Y Feng, Yang
%Y Xiong, Deyi
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F tahir-etal-2024-jora
%X The scaling of Large Language Models (LLMs) for retrieval-based tasks, particularly in Retrieval Augmented Generation (RAG), faces significant memory constraints, especially when fine-tuning extensive prompt sequences. Current open-source libraries support full-model inference and fine-tuning across multiple GPUs but fall short of accommodating the efficient parameter distribution required for retrieved context. Addressing this gap, we introduce a novel framework for PEFT-compatible fine-tuning of GPT models, leveraging distributed training. Our framework uniquely utilizes JAX’s just-in-time (JIT) compilation and tensor-sharding for efficient resource management, thereby enabling accelerated fine-tuning with reduced memory requirements. This advancement significantly improves the scalability and feasibility of fine-tuning LLMs for complex RAG applications, even on systems with limited GPU resources. Our experiments show more than 12x improvement in runtime compared to Hugging Face/DeepSpeed implementation with four GPUs while consuming less than half the VRAM per GPU.
%R 10.18653/v1/2024.acl-demos.15
%U https://aclanthology.org/2024.acl-demos.15
%U https://doi.org/10.18653/v1/2024.acl-demos.15
%P 152-159

Markdown (Informal)

[JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning](https://aclanthology.org/2024.acl-demos.15) (Tahir et al., ACL 2024)

• JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning (Tahir et al., ACL 2024)

ACL

• Anique Tahir, Lu Cheng, and Huan Liu. 2024. JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 152–159, Bangkok, Thailand. Association for Computational Linguistics.