FoldGPT: Simple and Effective Large Language Model Compression Scheme

• URL: http://arxiv.org/abs/2407.00928v1
• Date: Mon, 1 Jul 2024 03:17:53 GMT
• Title: FoldGPT: Simple and Effective Large Language Model Compression Scheme
• Authors: Songwei Liu, Chao Zeng, Lianqiang Li, Chenqian Yan, Lean Fu, Xing Mei, Fangmin Chen,
• Abstract summary: Network bandwidth and memory limitations pose challenges for deploying billion-level models on mobile devices. We propose FoldGPT, which combines block removal and block parameter sharing. Experiments demonstrate that FoldGPT outperforms previous state-of-the-art(SOTA) methods in efficient model compression.
• Score: 5.611544096046119
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The demand for deploying large language models(LLMs) on mobile devices continues to increase, driven by escalating data security concerns and cloud costs. However, network bandwidth and memory limitations pose challenges for deploying billion-level models on mobile devices. In this study, we investigate the outputs of different layers across various scales of LLMs and found that the outputs of most layers exhibit significant similarity. Moreover, this similarity becomes more pronounced as the model size increases, indicating substantial redundancy in the depth direction of the LLMs. Based on this observation, we propose an efficient model volume compression strategy, termed FoldGPT, which combines block removal and block parameter sharing.This strategy consists of three parts: (1) Based on the learnable gating parameters, we determine the block importance ranking while modeling the coupling effect between blocks. Then we delete some redundant layers based on the given removal rate. (2) For the retained blocks, we apply a specially designed group parameter sharing strategy, where blocks within the same group share identical weights, significantly compressing the number of parameters and slightly reducing latency overhead. (3) After sharing these Blocks, we "cure" the mismatch caused by sparsity with a minor amount of fine-tuning and introduce a tail-layer distillation strategy to improve the performance. Experiments demonstrate that FoldGPT outperforms previous state-of-the-art(SOTA) methods in efficient model compression, demonstrating the feasibility of achieving model lightweighting through straightforward block removal and parameter sharing.

Related papers

• FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing [59.12511498024836]
  We present a method to prune large language models (LLMs) that selectively prunes model blocks based on an importance score. We propose a principled metric to replace each pruned block using a weight-sharing mechanism. Empirical evaluations demonstrate substantial performance gains over existing methods.
  arXiv  Detail & Related papers  (2025-01-24T18:46:37Z)
• Learning Parameter Sharing with Tensor Decompositions and Sparsity [5.73573685846194]
  We introduce Fine-grained Singular Sharing (FiPS) to compress large-scale Vision Transformers (ViTs) and Large Language Models (LLMs) FiPS employs a shared base and sparse factors to represent neurons across multi-layer perceptron (MLP) modules. Experimental results show that FiPS reduces the parameter budget by 50-75% for DeiT-B and Swin-L and by 40-50% for various Gemma-2 and Llama-3 models.
  arXiv  Detail & Related papers  (2024-11-14T21:29:58Z)
• Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss [59.835032408496545]
  We propose a tile-based strategy that partitions the contrastive loss calculation into arbitrary small blocks. We also introduce a multi-level tiling strategy to leverage the hierarchical structure of distributed systems. Compared to SOTA memory-efficient solutions, it achieves a two-order-of-magnitude reduction in memory while maintaining comparable speed.
  arXiv  Detail & Related papers  (2024-10-22T17:59:30Z)
• SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers [88.68985153780514]
  We propose a new selective PEFT method, namely SparseGrad, that performs well on parameter blocks. We apply SparseGrad to fine-tune BERT and RoBERTa for the NLU task and LLaMa-2 for the Question-Answering task.
  arXiv  Detail & Related papers  (2024-10-09T19:03:52Z)
• MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards [35.163843138935455]
  The rapid scaling of large language models requires more lightweight finetuning methods to reduce the explosive GPU memory overhead. Our research highlights the indispensable role of differentiation in reversing the detrimental effects of pure sharing. We propose Mixture of Shards (MoS), incorporating both inter-layer and intra-layer sharing schemes, and integrating four nearly cost-free differentiation strategies.
  arXiv  Detail & Related papers  (2024-10-01T07:47:03Z)
• Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models [66.1595537904019]
  Large language models (LLMs) can act as gradient priors in a zero-shot setting. We introduce LM-GC, a novel method that integrates LLMs with arithmetic coding.
  arXiv  Detail & Related papers  (2024-09-26T13:38:33Z)
• MoDeGPT: Modular Decomposition for Large Language Model Compression [59.361006801465344]
  This paper introduces textbfModular bfDecomposition (MoDeGPT), a novel structured compression framework. MoDeGPT partitions the Transformer block into modules comprised of matrix pairs and reduces the hidden dimensions. Our experiments show MoDeGPT, without backward propagation, matches or surpasses previous structured compression methods.
  arXiv  Detail & Related papers  (2024-08-19T01:30:14Z)
• ShortGPT: Layers in Large Language Models are More Redundant Than You Expect [38.148626520751385]
  We show that many layers of Large Language Models (LLMs) exhibit high similarity, and some layers play a negligible role in network functionality. We propose a straightforward pruning approach: layer removal, in which we directly delete the redundant layers. Experiments demonstrate that our method, which we call ShortGPT, significantly outperforms previous state-of-the-art (SOTA) methods in model pruning.
  arXiv  Detail & Related papers  (2024-03-06T17:04:18Z)
• Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model [81.55141188169621]
  We equip PEFT with a cross-block orchestration mechanism to enable the adaptation of the Segment Anything Model (SAM) to various downstream scenarios. We propose an intra-block enhancement module, which introduces a linear projection head whose weights are generated from a hyper-complex layer. Our proposed approach consistently improves the segmentation performance significantly on novel scenarios with only around 1K additional parameters.
  arXiv  Detail & Related papers  (2023-11-28T11:23:34Z)
• Lightweight Diffusion Models with Distillation-Based Block Neural Architecture Search [55.41583104734349]
  We propose to automatically remove structural redundancy in diffusion models with our proposed Diffusion Distillation-based Block-wise Neural Architecture Search (NAS) Given a larger pretrained teacher, we leverage DiffNAS to search for the smallest architecture which can achieve on-par or even better performance than the teacher. Different from previous block-wise NAS methods, DiffNAS contains a block-wise local search strategy and a retraining strategy with a joint dynamic loss.
  arXiv  Detail & Related papers  (2023-11-08T12:56:59Z)
• CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model [22.870512676002463]
  This paper focuses on Offsite-Tuning (OFT), a representative technique that transfers transformer blocks between centralized LLMs and downstream emulators. Inspired by these observations, we propose CRaSh, involving Clustering, Removing, and Sharing, a training-free strategy to derive improved emulators from LLMs. Our findings demonstrate a linear connectivity among these optima falling over the same basin, thereby highlighting the effectiveness of CRaSh and OFT.
  arXiv  Detail & Related papers  (2023-10-24T03:08:58Z)
• Just CHOP: Embarrassingly Simple LLM Compression [27.64461490974072]
  Large language models (LLMs) enable unparalleled few- and zero-shot reasoning capabilities but at a high computational footprint. We show that simple layer pruning coupled with an extended language model pretraining produces state-of-the-art results against structured and even semi-structured compression of models at a 7B scale. We also show how distillation, which has been super effective in task-agnostic compression of smaller BERT-style models, becomes inefficient against our simple pruning technique.
  arXiv  Detail & Related papers  (2023-05-24T08:18:35Z)
• Scaling strategies for on-device low-complexity source separation with Conv-Tasnet [8.40565031143262]
  Several very effective neural approaches for single-channel speech separation have been presented in the literature. Due to the size and complexity of these models, their use on low-resource devices, e.g. for hearing aids, and earphones, is still a challenge. We consider three parameters that directly control the overall size of the model, namely: the number of residual blocks, the number of repetitions of the separation blocks and the number of channels in the depth-wise convolutions.
  arXiv  Detail & Related papers  (2023-03-06T10:15:14Z)

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.