paper-with-me

Papers

Streamlining Redundant Layers to Compress Large Language Models

2024-03-28 · Xiaodong Chen, Yuxuan Hu, Jing Zhang, Yanling Wang, Cuiping Li, Hong Chen

This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less important layers to be pruned.LLM-Streamline comprises two parts: layer pruning, which removes consecutive layers with the lowest importance based on target sparsity, and layer replacement, a novel module that trains a lightweight network to replace the pruned layers to mitigate performance loss. Additionally, a new metric called stability is proposed to address the limitations of the widely used accuracy metric in evaluating model compression. Experiments show that LLM-Streamline outperforms both previous and concurrent state-of-the-art pruning methods in terms of both performance and training efficiency.Our code is available at https://github.com/RUCKBReasoning/LLM-Streamline

📄 PDF Abstract BibTeX arXiv:2403.19135

Code (1)

ruckbreasoning/llm-streamline 공식 구현 pytorch

Tasks

Model Compression

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Enhancing Inference Efficiency of Large Language Models: Investigating Optimization Strategies and Architectural Innovations

2024-04-02 · Georgy Tyukin

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is impo…

Model Compression

Layer Collapse in Diffusion Language Models

2026-05-07 · Alexander Conzelmann, Albert Catalan-Tatjer, Shiwei Liu arxiv

Diffusion language models (DLMs) have recently emerged as competitive alternatives to autoregressive (AR) language models, yet differences in their activation dynamics remain poorly understood. We characterize these dyna…

Towards Understanding Layer Contributions in Tabular In-Context Learning Models

2025-11-19 · Amir Rezaei Balef, Mykhailo Koshil, Katharina Eggensperger arxiv

Despite the architectural similarities between tabular in-context learning (ICL) models and large language models (LLMs), little is known about how individual layers contribute to tabular prediction. In this paper, we in…

Model Compression

Layer-wise dynamic rank for compressing large language models

2025-09-30 · Zhendong Mi, Bian Sun, Grace Li Zhang, Shaoyi Huang arxiv

Large language models (LLMs) have rapidly scaled in size, bringing severe memory and computational challenges that hinder their deployment. Singular Value Decomposition (SVD)-based compression has emerged as an appealing…

CASP: Compression of Large Multimodal Models Based on Attention Sparsity

2025-03-07 · CVPR 2025 1 · Mohsen Gholami, Mohammad Akbari, Kevin Cannons, Yong Zhang

In this work, we propose an extreme compression technique for Large Multimodal Models (LMMs). While previous studies have explored quantization as an efficient post-training compression method for Large Language Models (…

Model CompressionQuantization