paper-with-me

홈 › Papers

OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models

2024-06-03 · Kerim Büyükakyüz

The advent of large language models (LLMs) has revolutionized natural language processing, enabling unprecedented capabilities in understanding and generating human-like text. However, the computational cost and convergence times associated with fine-tuning these models remain significant challenges. Low-Rank Adaptation (LoRA) has emerged as a promising method to mitigate these issues by introducing efficient fine-tuning techniques with a reduced number of trainable parameters. In this paper, we present OLoRA, an enhancement to the LoRA method that leverages orthonormal matrix initialization through QR decomposition. OLoRA significantly accelerates the convergence of LLM training while preserving the efficiency benefits of LoRA, such as the number of trainable parameters and GPU memory footprint. Our empirical evaluations demonstrate that OLoRA not only converges faster but also exhibits improved performance compared to standard LoRA across a variety of language modeling tasks. This advancement opens new avenues for more efficient and accessible fine-tuning of LLMs, potentially enabling broader adoption and innovation in natural language applications.

📄 PDF Abstract BibTeX arXiv:2406.01775

Code (0)

등록된 구현이 없습니다.

Tasks

GPULanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning

2024-03-14 · Ruiyi Zhang, Rushi Qiang, Sai Ashish Somayajula, Pengtao Xie

Large-scale pretraining followed by task-specific finetuning has achieved great success in various NLP tasks. Since finetuning all parameters of large pretrained models poses substantial computational and memory challeng…

Meta-LearningNatural Language Understanding

PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA

2024-02-24 · Sheng Wang, Boyang Xue, Jiacheng Ye, Jiyue Jiang 외

With the rapid scaling of large language models (LLMs), serving numerous low-rank adaptations (LoRAs) concurrently has become increasingly impractical, leading to unaffordable costs and necessitating more parameter-effic…

CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations

2024-02-22 · Jules Berman, Benjamin Peherstorfer

This work introduces reduced models based on Continuous Low Rank Adaptation (CoLoRA) that pre-train neural networks for a given partial differential equation and then continuously adapt low-rank weights in time to rapidl…

Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR

2026-06-30 · Ruijia Zhang, Jiacheng Zhu, Hanqing Zhu, Laixi Shi arxiv

Low-rank adaptation (LoRA) and its variants enable parameter-efficient fine-tuning of large language models under the supervised fine-tuning (SFT) paradigm. However, their efficacy and behavior under Reinforcement learni…

parameter-efficient fine-tuningReinforcement LearningMathematical Reasoning

GeoLoRA: Geometric integration for parameter efficient fine-tuning

2024-10-24 · Steffen Schotthöfer, Emanuele Zangrando, Gianluca Ceruti, Francesco Tudisco 외

Low-Rank Adaptation (LoRA) has become a widely used method for parameter-efficient fine-tuning of large-scale, pre-trained neural networks. However, LoRA and its extensions face several challenges, including the need for…

Computational Efficiencyparameter-efficient fine-tuning