Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging

• URL: http://arxiv.org/abs/2406.16330v1
• Date: Mon, 24 Jun 2024 05:57:55 GMT
• Title: Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
• Authors: Deyuan Liu, Zhanyue Qin, Hairu Wang, Zhao Yang, Zecheng Wang, Fangying Rong, Qingbin Liu, Yanchao Hao, Xi Chen, Cunhang Fan, Zhao Lv, Zhiying Tu, Dianhui Chu, Bo Li, Dianbo Sui,
• Abstract summary: We propose Manifold-Based Knowledge Alignment and Layer Merging Compression (MKA) MKA uses manifold learning and the Normalized Pairwise Information Bottleneck measure to merge similar layers, reducing model size while preserving essential performance. Our findings show that MKA not only preserves model performance but also achieves substantial compression ratios, outperforming traditional pruning methods.
• Score: 14.123313596780726
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models (LLMs) excel in many domains, their complexity and scale challenge deployment in resource-limited environments. Current compression techniques, such as parameter pruning, often fail to effectively utilize the knowledge from pruned parameters. To address these challenges, we propose Manifold-Based Knowledge Alignment and Layer Merging Compression (MKA), a novel approach that uses manifold learning and the Normalized Pairwise Information Bottleneck (NPIB) measure to merge similar layers, reducing model size while preserving essential performance. We evaluate MKA on multiple benchmark datasets and various LLMs. Our findings show that MKA not only preserves model performance but also achieves substantial compression ratios, outperforming traditional pruning methods. Moreover, when coupled with quantization, MKA delivers even greater compression. Specifically, on the MMLU dataset using the Llama3-8B model, MKA achieves a compression ratio of 43.75% with a minimal performance decrease of only 2.82\%. The proposed MKA method offers a resource-efficient and performance-preserving model compression technique for LLMs.

Related papers

• Pushing the Limits of Large Language Model Quantization via the Linearity Theorem [71.3332971315821]
  We present a "line theoremarity" establishing a direct relationship between the layer-wise $ell$ reconstruction error and the model perplexity increase due to quantization. This insight enables two novel applications: (1) a simple data-free LLM quantization method using Hadamard rotations and MSE-optimal grids, dubbed HIGGS, and (2) an optimal solution to the problem of finding non-uniform per-layer quantization levels.
  arXiv  Detail & Related papers  (2024-11-26T15:35:44Z)
• MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition [32.97035551579975]
  We introduce a two-stage compression method tailored for MoE to reduce the model size and decrease the computational cost. Experiments on Qwen1.5-MoE-A2.7B, DeepSeek-V2-Lite, and Mixtral-8$times$7B demonstrate that our proposed methods can both reduce the model size and enhance inference efficiency.
  arXiv  Detail & Related papers  (2024-11-01T20:37:58Z)
• SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching [32.4599581528901]
  "Two-tower" architecture is used for compressing pre-trained LLM parameters into compact representations and fine-tuning the additive full-precision adapter. We propose SpaLLM (Sketched Adapting of LLMs), a novel compressive adaptation approach for LLMs. We show that SpaLLM sketches pre-trained LLM weights into lookup tables and directly fine-tunes the values in these tables.
  arXiv  Detail & Related papers  (2024-10-08T20:58:24Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression [5.206085750261924]
  Large Language Models (LLMs) require significant amount of memory storage in inference. In this paper, we take a step further to explore parameter sharing across different layers with singular value decomposition. Comprehensive experiments demonstrate that Basis Sharing outperforms state-of-the-art SVD-based compression approaches.
  arXiv  Detail & Related papers  (2024-10-02T14:30:02Z)
• 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)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization [40.15915011575071]
  Low-rank compression is a promising technique to reduce non-essential parameters in large language models. We conduct empirical research on the low-rank characteristics of large models. We propose a low-rank compression method suitable for large language models.
  arXiv  Detail & Related papers  (2024-05-17T08:27:12Z)
• The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models [11.156816338995503]
  Large language models (LLMs) provide faster inference, smaller memory footprints, and enables local deployment. Two standard compression techniques are pruning and quantization, with the former eliminating redundant connections in model layers and the latter representing model parameters with fewer bits. Existing research on LLM compression primarily focuses on performance in terms of general metrics like perplexity or downstream task accuracy. More fine-grained metrics, such as those measuring parametric knowledge, remain significantly underexplored.
  arXiv  Detail & Related papers  (2023-12-01T22:27:12Z)
• Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression [64.07696663255155]
  Large-scale pre-trained language models (LLMs) have demonstrated exceptional performance in various natural language processing (NLP) tasks. However, the massive size of these models poses huge challenges for their deployment in real-world applications. We introduce a novel compression paradigm called Retrieval-based Knowledge Transfer (RetriKT) which effectively transfers the knowledge of LLMs to extremely small-scale models.
  arXiv  Detail & Related papers  (2023-10-24T07:58:20Z)
• Compressing LLMs: The Truth is Rarely Pure and Never Simple [90.05366363633568]
  Knowledge-Intensive Compressed LLM BenchmarK aims to redefine the evaluation protocol for compressed Large Language Models. LLM-KICK unveils many favorable merits and unfortunate plights of current SoTA compression methods. LLM-KICK is designed to holistically access compressed LLMs' ability for language understanding, reasoning, generation, in-context retrieval, in-context summarization, etc.
  arXiv  Detail & Related papers  (2023-10-02T17:42:37Z)

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.