NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models

• URL: http://arxiv.org/abs/2402.09773v2
• Date: Thu, 27 Jun 2024 04:49:11 GMT
• Title: NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models
• Authors: Shengrui Li, Junzhe Chen, Xueting Han, Jing Bai,
• Abstract summary: We propose an efficient progressive Numerous-teacher pruning method (NutePrune) NutePrune mitigates excessive memory costs by loading only one intact model and integrating it with various masks and LoRA modules. In LLaMA-7B experiments, NutePrune retains 97.17% of the performance of the original model at 20% sparsity and 95.07% at 25% sparsity.
• Score: 2.9449838351181374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The considerable size of Large Language Models (LLMs) presents notable deployment challenges, particularly on resource-constrained hardware. Structured pruning, offers an effective means to compress LLMs, thereby reducing storage costs and enhancing inference speed for more efficient utilization. In this work, we study data-efficient and resource-efficient structure pruning methods to obtain smaller yet still powerful models. Knowledge Distillation is well-suited for pruning, as the intact model can serve as an excellent teacher for pruned students. However, it becomes challenging in the context of LLMs due to memory constraints. To address this, we propose an efficient progressive Numerous-teacher pruning method (NutePrune). NutePrune mitigates excessive memory costs by loading only one intact model and integrating it with various masks and LoRA modules, enabling it to seamlessly switch between teacher and student roles. This approach allows us to leverage numerous teachers with varying capacities to progressively guide the pruned model, enhancing overall performance. Extensive experiments across various tasks demonstrate the effectiveness of NutePrune. In LLaMA-7B zero-shot experiments, NutePrune retains 97.17% of the performance of the original model at 20% sparsity and 95.07% at 25% sparsity. Our code is available at https://github.com/Lucius-lsr/NutePrune.

Related papers

• Parameter-Efficient Fine-Tuning of Large Language Models for Unit Test Generation: An Empirical Study [3.5189934649278922]
  Large language models (LLMs) like GitHub Copilot struggle with real-world tasks without fine-tuning. This paper investigates full fine-tuning and various PEFT methods, including LoRA, (IA)3, and prompt tuning. Our findings show that PEFT methods can deliver performance comparable to full fine-tuning for unit test generation.
  arXiv  Detail & Related papers  (2024-11-04T09:03:18Z)
• MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router [55.88046193872355]
  Mixture-of-Experts (MoE) architectures face challenges such as high memory consumption and redundancy in experts. We propose MoE-Pruner, a method that prunes weights with the smallest magnitudes multiplied by the corresponding input activations and router weights. Our pruning method is one-shot, requiring no retraining or weight updates.
  arXiv  Detail & Related papers  (2024-10-15T19:22:27Z)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• PAT: Pruning-Aware Tuning for Large Language Models [19.622152991641045]
  Large language models excel in language tasks, especially with supervised fine-tuning after pre-training. Traditional post-hoc pruning often leads to significant performance loss. We propose the Pruning-Aware Tuning (PAT) paradigm to eliminate model redundancy.
  arXiv  Detail & Related papers  (2024-08-27T01:04:14Z)
• PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs [47.35598271306371]
  Large Language Models (LLMs) have exhibited impressive capabilities in various tasks, yet their vast parameter sizes restrict their applicability in resource-constrained settings. Knowledge distillation (KD) offers a viable solution by transferring expertise from large teacher models to compact student models. We present PLaD, a novel preference-based LLM distillation framework.
  arXiv  Detail & Related papers  (2024-06-05T03:08:25Z)
• SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models [53.638791265113625]
  Sparsity-Preserved efficient fine-tuning method for large language models. Code will be made available at https://github.com/Lucky-Lance/SPP.
  arXiv  Detail & Related papers  (2024-05-25T04:55:27Z)
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models [90.14693869269519]
  MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. This paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques.
  arXiv  Detail & Related papers  (2024-02-22T18:56:07Z)
• Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods [5.135352292810664]
  We show that simple depth pruning can effectively compress large language models (LLMs) Our pruning method boosts inference speeds, especially under memory-constrained conditions. We hope this work can help build compact yet capable LLMs.
  arXiv  Detail & Related papers  (2024-02-05T09:44:49Z)
• LiST: Lite Self-training Makes Efficient Few-shot Learners [91.28065455714018]
  LiST improves by 35% over classic fine-tuning methods and 6% over prompt-tuning with 96% reduction in number of trainable parameters when fine-tuned with no more than 30 labeled examples from each target domain.
  arXiv  Detail & Related papers  (2021-10-12T18:47:18Z)
• DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning [94.89221799550593]
  Self-supervised representation learning (SSL) has received widespread attention from the community. Recent research argue that its performance will suffer a cliff fall when the model size decreases. We propose a simple yet effective Distilled Contrastive Learning (DisCo) to ease the issue by a large margin.
  arXiv  Detail & Related papers  (2021-04-19T08:22:52Z)

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.