LoRA-Mini : Adaptation Matrices Decomposition and Selective Training
- URL: http://arxiv.org/abs/2411.15804v1
- Date: Sun, 24 Nov 2024 12:21:14 GMT
- Title: LoRA-Mini : Adaptation Matrices Decomposition and Selective Training
- Authors: Ayush Singh, Rajdeep Aher, Shivank Garg,
- Abstract summary: Low-Rank Adaptation (LoRA) has emerged as a promising solution, enabling parameter-efficient fine-tuning by reducing the number of trainable parameters.
We propose LoRA-Mini, an optimized adaptation of LoRA that improves parameter efficiency by splitting low-rank matrices into four parts.
This approach achieves upto a 20x reduction compared to standard LoRA in the number of trainable parameters while preserving performance levels comparable to standard LoRA.
- Score: 2.0670689746336
- License:
- Abstract: The rapid advancements in large language models (LLMs) have revolutionized natural language processing, creating an increased need for efficient, task-specific fine-tuning methods. Traditional fine-tuning of LLMs involves updating a large number of parameters, which is computationally expensive and memory-intensive. Low-Rank Adaptation (LoRA) has emerged as a promising solution, enabling parameter-efficient fine-tuning by reducing the number of trainable parameters. However, while LoRA reduces the number of trainable parameters, LoRA modules still create significant storage challenges. We propose LoRA-Mini, an optimized adaptation of LoRA that improves parameter efficiency by splitting low-rank matrices into four parts, with only the two inner matrices being trainable. This approach achieves upto a 20x reduction compared to standard LoRA in the number of trainable parameters while preserving performance levels comparable to standard LoRA, addressing both computational and storage efficiency in LLM fine-tuning.
Related papers
- RandLoRA: Full-rank parameter-efficient fine-tuning of large models [46.25124374446935]
Low-Rank Adaptation (LoRA) and its variants have shown impressive results in reducing the number of trainable parameters and memory requirements of large transformer networks.
However, the low-rank nature of the weight update inherently limits the representation power of fine-tuned models.
This paper introduces RandLoRA, a method that performs full-rank updates using a learned linear combinations of low-rank, non-trainable random matrices.
arXiv Detail & Related papers (2025-02-03T01:59:45Z) - GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning [2.7446241148152253]
Fine-tuning large language models (LLMs) is computationally intensive because it requires updating all parameters.
Low-Rank Adaptation (LoRA) improves efficiency by modifying only a subset of weights but introduces a trade-off between expressivity and computational cost.
We propose Geometric Low-Rank Adaptation (GeLoRA), a novel framework that computes the intrinsic dimensionality of hidden state representations to adaptively select LoRA ranks.
arXiv Detail & Related papers (2024-12-12T13:04:54Z) - LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization [78.93425154518705]
Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements.
This paper introduces LoRA-RITE, a novel adaptive matrix preconditioning method for LoRA optimization.
arXiv Detail & Related papers (2024-10-27T22:57:12Z) - Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs [75.11449420928139]
Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks.
Low-Rank Adaptation (LoRA) has emerged as a promising solution, but there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum.
We propose eXtreme Gradient Boosting LoRA, a novel framework that bridges this gap by leveraging the power of ensemble learning.
arXiv Detail & Related papers (2024-10-25T17:07:13Z) - LoRTA: Low Rank Tensor Adaptation of Large Language Models [70.32218116940393]
Low Rank Adaptation (LoRA) is a popular Efficient Fine Tuning (PEFT) method.
We propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation.
Our method can achieve a reduction in the number of parameters while maintaining comparable performance.
arXiv Detail & Related papers (2024-10-05T06:59:50Z) - LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters [11.23006032094776]
We introduce LoRA-XS, a novel low-rank adaptation method that considerably reduces the trainable parameters while showing superior or competitive performance.
LoRA-XS achieves a remarkable reduction of trainable parameters by over 100x in 7B models compared to LoRA.
arXiv Detail & Related papers (2024-05-27T19:07:13Z) - MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning [105.11844150736536]
Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models.
We propose a new method called MoRA, which employs a square matrix to achieve high-rank updating while maintaining the same number of trainable parameters.
Our method outperforms LoRA on memory-intensive tasks and achieves comparable performance on other tasks.
arXiv Detail & Related papers (2024-05-20T15:48:32Z) - MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning [71.50432879573614]
Low-rank adaptation (LoRA) is based on the idea that the adaptation process is intrinsically low-dimensional.
We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank.
Our experimental results show that, compared to LoRA, MELoRA achieves better performance with 8 times fewer trainable parameters on natural language understanding tasks and 36 times fewer trainable parameters on instruction following tasks.
arXiv Detail & Related papers (2024-02-27T07:14:12Z) - Chain of LoRA: Efficient Fine-tuning of Language Models via Residual
Learning [31.036465632204663]
We introduce Chain of LoRA, an iterative optimization framework inspired by the Frank-Wolfe algorithm.
We demonstrate that COLA can consistently outperform LoRA without additional computational or memory costs.
arXiv Detail & Related papers (2024-01-08T14:26:49Z) - IncreLoRA: Incremental Parameter Allocation Method for
Parameter-Efficient Fine-tuning [15.964205804768163]
IncreLoRA is an incremental parameter allocation method that adaptively adds trainable parameters during training.
We conduct extensive experiments on GLUE to demonstrate the effectiveness of IncreLoRA.
arXiv Detail & Related papers (2023-08-23T10:08:10Z)
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.