PAT: Pruning-Aware Tuning for Large Language Models
Large language models (LLMs) excel in language tasks, especially with supervised fine-tuning after pre-training. However, their substantial memory and computational requirements hinder practical applications. Structural pruning, which reduces less significant weight dimensions, is one solution. Yet, traditional post-hoc pruning often leads to significant performance loss, with limited recovery from further fine-tuning due to reduced capacity. Since the model fine-tuning refines the general and chaotic knowledge in pre-trained models, we aim to incorporate structural pruning with the fine-tuning, and propose the Pruning-Aware Tuning (PAT) paradigm to eliminate model redundancy while preserving the model performance to the maximum extend. Specifically, we insert the innovative Hybrid Sparsification Modules (HSMs) between the Attention and FFN components to accordingly sparsify the upstream and downstream linear modules. The HSM comprises a lightweight operator and a globally shared trainable mask. The lightweight operator maintains a training overhead comparable to that of LoRA, while the trainable mask unifies the channels to be sparsified, ensuring structural pruning. Additionally, we propose the Identity Loss which decouples the transformation and scaling properties of the HSMs to enhance training robustness. Extensive experiments demonstrate that PAT excels in both performance and efficiency. For example, our Llama2-7b model with a 25\% pruning ratio achieves 1.33$\times$ speedup while outperforming the LoRA-finetuned model by up to 1.26\% in accuracy with a similar training cost. Code: https://github.com/kriskrisliu/PAT_Pruning-Aware-Tuning
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Wanda++: Pruning Large Language Models via Regional Gradients
Large Language Models (LLMs) pruning seeks to remove unimportant weights for inference speedup with minimal performance impact. However, existing methods often suffer from performance loss without full-model sparsity-awa…
DecoderGPULanguage ModelingLanguage ModellingPrior Gradient Mask Guided Pruning-Aware Fine-Tuning
We proposed a Prior Gradient Mask Guided Pruning-aware Fine-Tuning (PGMPF) framework to accelerate deep Convolutional Neural Networks (CNNs). In detail, the proposed PGMPF selectively suppresses the gradient of those ”un…
image-classificationImage ClassificationAll-in-One Tuning and Structural Pruning for Domain-Specific LLMs
Existing pruning techniques for large language models (LLMs) targeting domain-specific applications typically follow a two-stage process: pruning the pretrained general-purpose LLMs and then fine-tuning the pruned LLMs o…
AllSparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models
Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-…
Model CompressionEfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning
Large language models (LLMs) are increasingly adapted into domain-specific variants for applications in law, healthcare, and finance. Their scale, however, limits deployment in resource-constrained settings, and existing…
Domain Adaptation