3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
- URL: http://arxiv.org/abs/2409.00119v2
- Date: Mon, 4 Nov 2024 09:07:25 GMT
- Title: 3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
- Authors: Baohao Liao, Christof Monz,
- Abstract summary: We introduce a novel method, RoAd, which employs a straightforward 2D rotation to adapt large language models (LLMs)
RoAd is remarkably parameter-efficient, delivering optimal performance on GLUE, eight commonsense reasoning tasks and four arithmetic reasoning tasks with $0.1%$ trainable parameters.
- Score: 6.451743797015637
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Parameter-efficient finetuning (PEFT) methods effectively adapt large language models (LLMs) to diverse downstream tasks, reducing storage and GPU memory demands. Despite these advantages, several applications pose new challenges to PEFT beyond mere parameter efficiency. One notable challenge involves the efficient deployment of LLMs equipped with multiple task- or user-specific adapters, particularly when different adapters are needed for distinct requests within the same batch. Another challenge is the interpretability of LLMs, which is crucial for understanding how LLMs function. Previous studies introduced various approaches to address different challenges. In this paper, we introduce a novel method, RoAd, which employs a straightforward 2D rotation to adapt LLMs and addresses all the above challenges: (1) RoAd is remarkably parameter-efficient, delivering optimal performance on GLUE, eight commonsense reasoning tasks and four arithmetic reasoning tasks with $<0.1\%$ trainable parameters; (2) RoAd facilitates the efficient serving of requests requiring different adapters within a batch, with an overhead comparable to element-wise multiplication instead of batch matrix multiplication; (3) RoAd enhances LLM's interpretability through integration within a framework of distributed interchange intervention, demonstrated via composition experiments.
Related papers
- Pilot: Building the Federated Multimodal Instruction Tuning Framework [79.56362403673354]
Our framework integrates two stages of "adapter on adapter" into the connector of the vision encoder and the LLM.
In stage 1, we extract task-specific features and client-specific features from visual information.
In stage 2, we build the cross-task Mixture-of-Adapters(CT-MoA) module to perform cross-task interaction.
arXiv Detail & Related papers (2025-01-23T07:49:24Z) - TriAdaptLoRA: Brain-Inspired Triangular Adaptive Low-Rank Adaptation for Parameter-Efficient Fine-Tuning [9.730075039461154]
Fine-tuning Large Language Models (LLMs) is pivotal for achieving optimal performance across diverse downstream tasks.
We propose Adaptive Low-Rank Adaptation (TriAdaptLoRA), a novel PEFT framework inspired by neuroscience principles.
Experiments conducted on a variety of natural language understanding and generation tasks demonstrate that TriAdaptLoRA consistently outperforms existing PEFT methods.
arXiv Detail & Related papers (2025-01-14T10:51:31Z) - Transformer-Squared: Self-adaptive LLMs [29.1326358746118]
We introduce Transformer-Squared, a novel self-adaptation framework that adapts large language models for unseen tasks in real-time.
Our method consistently outperforms ubiquitous approaches such as LoRA, with fewer parameters and greater efficiency.
Transformer-Squared represents a significant leap forward, offering a scalable, efficient solution for enhancing the adaptability and task-specific performance of LLMs.
arXiv Detail & Related papers (2025-01-09T01:19:21Z) - Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System [75.25394449773052]
Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving.
Yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods.
We present Optima, a novel framework that addresses these issues by significantly enhancing both communication efficiency and task effectiveness.
arXiv Detail & Related papers (2024-10-10T17:00:06Z) - MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization [73.7779735046424]
We show that different prompts should be adapted to different Large Language Models (LLM) to enhance their capabilities across various downstream tasks in NLP.
We then propose a model-adaptive prompt (MAPO) method that optimize the original prompts for each specific LLM in downstream tasks.
arXiv Detail & Related papers (2024-07-04T18:39:59Z) - ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization [13.622268474310918]
ShiftAddLLM is an efficient multiplication-free model for large language models.
It achieves perplexity improvements of 5.6 and 22.7 points at comparable or lower latency.
Experiments on five LLM families and eight tasks consistently validate the effectiveness of ShiftAddLLM.
arXiv Detail & Related papers (2024-06-10T02:47:55Z) - CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion [58.15403987979496]
CREMA is a generalizable, highly efficient, and modular modality-fusion framework for video reasoning.
We propose a novel progressive multimodal fusion design supported by a lightweight fusion module and modality-sequential training strategy.
We validate our method on 7 video-language reasoning tasks assisted by diverse modalities, including VideoQA and Video-Audio/3D/Touch/Thermal QA.
arXiv Detail & Related papers (2024-02-08T18:27:22Z) - When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications [57.342772288710044]
We propose a novel parameter efficient fine-tuning framework for multi-task medical applications, dubbed as MOELoRA.
For unifying MOE and LoRA, we devise multiple experts as the trainable parameters, where each expert consists of a pair of low-rank matrices to retain the small size of trainable parameters.
We conduct experiments on a multi-task medical dataset, indicating MOELoRA outperforms the existing parameter efficient fine-tuning methods.
arXiv Detail & Related papers (2023-10-21T17:18:09Z) - ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale [18.396897413970965]
ScaLearn is a simple and highly parameter-efficient two-stage MTL method.
We show that ScaLearn consistently outperforms strong baselines with a small number of transfer parameters.
arXiv Detail & Related papers (2023-10-02T14:01:36Z) - LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of
Large Language Models [75.25782573728677]
This paper presents a framework for adapter-based parameter-efficient fine-tuning (PEFT) of language models (LLMs)
The framework includes state-of-the-art open-access LLMs such as LLaMA, BLOOM, and GPT-J, as well as widely used adapters such as Series adapters, Parallel adapter, Prompt-based learning and Reparametrization-based methods.
We evaluate the effectiveness of the adapters on fourteen datasets from two different reasoning tasks, Arithmetic Reasoning and Commonsense Reasoning.
arXiv Detail & Related papers (2023-04-04T16:31:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.