paper-with-me

홈 › Papers

KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation

2024-10-28 · Rambod Azimi, Rishav Rishav, Marek Teichmann, Samira Ebrahimi Kahou

Large language models (LLMs) have demonstrated remarkable performance across various downstream tasks. However, the high computational and memory requirements of LLMs are a major bottleneck. To address this, parameter-efficient fine-tuning (PEFT) methods such as low-rank adaptation (LoRA) have been proposed to reduce computational costs while ensuring minimal loss in performance. Additionally, knowledge distillation (KD) has been a popular choice for obtaining compact student models from teacher models. In this work, we present KD-LoRA, a novel fine-tuning method that combines LoRA with KD. Our results demonstrate that KD-LoRA achieves performance comparable to full fine-tuning (FFT) and LoRA while significantly reducing resource requirements. Specifically, KD-LoRA retains 98% of LoRA's performance on the GLUE benchmark, while being 40% more compact. Additionally, KD-LoRA reduces GPU memory usage by 30% compared to LoRA, while decreasing inference time by 30% compared to both FFT and LoRA. We evaluate KD-LoRA across three encoder-only models: BERT, RoBERTa, and DeBERTaV3. Code is available at https://github.com/rambodazimi/KD-LoRA.

📄 PDF Abstract BibTeX arXiv:2410.20777

Code (1)

rambodazimi/kd-lora 공식 구현 pytorch

Tasks

GPUKnowledge Distillationparameter-efficient fine-tuning

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Adam 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Weight Decay 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Kron-LoRA: Hybrid Kronecker-LoRA Adapters for Scalable, Sustainable Fine-tuning

2025-08-04 · Yixin Shen arxiv

Fine-tuning massive pre-trained language models across many tasks demands adapters that are both parameter-efficient and expressive. We introduce \textbf{Kron-LoRA}, a hybrid adapter that combines Kronecker-structured fa…

parameter-efficient fine-tuning

Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training

2026-05-12 · Chengqian Zhang, Wei Zhu, Kyumin Lee arxiv

Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step reasoning. Reinforcement learning with v…

parameter-efficient fine-tuningReinforcement LearningInstruction Following

HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture

2025-02-27 · Taiqiang Wu, Chenchen Ding, Wenyong Zhou, Yuxin Cheng 외

Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method to adapt large language models (LLMs) for downstream tasks. In this paper, we first propose to deploy the LoRA-finetuned LLMs on the hybri…

SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA

2025-05-29 · Minrui Luo, Fuhang Kuang, Yu Wang, Zirui Liu 외

Parameter-Efficient Fine-Tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), are indispensable for efficiently customizing Large Language Models (LLMs). However, vanilla LoRA suffers from slow convergence spe…

Navigateparameter-efficient fine-tuningWorld Knowledge

ProtoBERT-LoRA: Parameter-Efficient Prototypical Finetuning for Immunotherapy Study Identification

2025-03-26 · Shijia Zhang, Xiyu Ding, Kai Ding, Jacob Zhang 외

Identifying immune checkpoint inhibitor (ICI) studies in genomic repositories like Gene Expression Omnibus (GEO) is vital for cancer research yet remains challenging due to semantic ambiguity, extreme class imbalance, an…