paper-with-me

홈 › Papers

Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models

2024-03-06 · Wenfeng Feng, Chuzhan Hao, Yuewei Zhang, Yu Han, Hao Wang

Instruction Tuning has the potential to stimulate or enhance specific capabilities of large language models (LLMs). However, achieving the right balance of data is crucial to prevent catastrophic forgetting and interference between tasks. To address these limitations and enhance training flexibility, we propose the Mixture-of-LoRAs (MoA) architecture which is a novel and parameter-efficient tuning method designed for multi-task learning with LLMs. In this paper, we start by individually training multiple domain-specific LoRA modules using corresponding supervised corpus data. These LoRA modules can be aligned with the expert design principles observed in Mixture-of-Experts (MoE). Subsequently, we combine the multiple LoRAs using an explicit routing strategy and introduce domain labels to facilitate multi-task learning, which help prevent interference between tasks and ultimately enhances the performance of each individual task. Furthermore, each LoRA model can be iteratively adapted to a new domain, allowing for quick domain-specific adaptation. Experiments on diverse tasks demonstrate superior and robust performance, which can further promote the wide application of domain-specific LLMs.

📄 PDF Abstract BibTeX arXiv:2403.03432

Code (1)

Leeroo-AI/mergoo pytorch

Tasks

Mixture-of-ExpertsMulti-Task Learning

Similar Papers 제목 키워드 기반

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning

2026-03-10 · Ruizhong Qiu, Hanqing Zeng, Yinglong Xia, Yiwen Meng 외 arxiv

Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRAs models expand neural networks efficien…

Reinforcement Learning

Learning Attentional Mixture of LoRAs for Language Model Continual Learning

2024-09-29 · Jialin Liu, Jianhua Wu, Jie Liu, Yutai Duan

Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dea…

Continual LearningLanguage ModelingLanguage Modelling

Mixture of LoRA Experts

2024-04-21 · Xun Wu, Shaohan Huang, Furu Wei

LoRA has gained widespread acceptance in the fine-tuning of large pre-trained models to cater to a diverse array of downstream tasks, showcasing notable effectiveness and efficiency, thereby solidifying its position as o…

Multi LoRA Meets Vision: Merging multiple adapters to create a multi task model

2024-11-21 · Ege Kesim, Selahattin Serdar Helli

Parameter efficient finetuning (PEFT) methods are widely used in LLMs and generative models in computer vision. Especially one can use multiple of these during inference to change the behavior of the base model. In this …

A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models

2025-02-20 · Mengyang Sun, Yihao Wang, Tao Feng, Dan Zhang 외

In order to streamline the fine-tuning of foundation models, Low-Rank Adapters (LoRAs) have been substantially adopted across various fields, including instruction tuning and domain adaptation. The underlying concept of …

Domain Adaptation