paper-with-me

Papers

Can pruning make Large Language Models more efficient?

2023-10-06 · Sia Gholami, marwan omar

Transformer models have revolutionized natural language processing with their unparalleled ability to grasp complex contextual relationships. However, the vast number of parameters in these models has raised concerns regarding computational efficiency, environmental impact, and deployability on resource-limited platforms. To address these challenges, this paper investigates the application of weight pruning-a strategic reduction of model parameters based on their significance-as an optimization strategy for Transformer architectures. Through extensive experimentation, we explore various pruning methodologies, highlighting their impact on model performance, size, and computational demands. Our findings suggest that with judicious selection of pruning hyperparameters, significant reductions in model size are attainable without considerable compromise on performance. Moreover, when coupled with post-pruning fine-tuning strategies, some pruned models even exhibit enhanced generalization capabilities. This work seeks to bridge the gap between model efficiency and performance, paving the way for more scalable and environmentally responsible deep learning applications.

📄 PDF Abstract BibTeX arXiv:2310.04573

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음

Similar Papers 제목 키워드 기반

FastAV: Efficient Token Pruning for Audio-Visual Large Language Model Inference

2026-01-19 · Chaeyoung Jung, Youngjoon Jang, Seungwoo Lee, Joon Son Chung arxiv

In this work, we present FastAV, the first token pruning framework tailored for audio-visual large language models (AV-LLMs). While token pruning has been actively explored in standard large language models (LLMs) and vi…

LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models

2025-01-23 · Yizheng Sun, Yanze Xin, Hao Li, Jingyuan Sun 외

Multi-modal Large Language Models (MLLMs) have achieved remarkable success by integrating visual and textual modalities. However, they incur significant computational overhead due to the large number of vision tokens pro…

Structured Pruning of Large Language Models

2019-10-10 · EMNLP 2020 11 · Ziheng Wang, Jeremy Wohlwend, Tao Lei

Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency have significantly increased, which makes t…

Language ModelingLanguage ModellingModel CompressionWord Embeddings

PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations

2022-03-31 · Lodagala V S V Durga Prasad, Sreyan Ghosh, S. Umesh

While self-supervised speech representation learning (SSL) models serve a variety of downstream tasks, these models have been observed to overfit to the domain from which the unlabelled data originates. To alleviate this…

Domain AdaptationLanguage ModellingRepresentation LearningSpeech Representation Learning

Variance Pruning: Pruning Language Models via Temporal Neuron Variance

2021-09-29 · Berry Weinstein, Yonatan Belinkov

As language models become larger, different pruning methods have been proposed to reduce model size. However, the typical sparsity patterns that are formed by commonly pruning regimes do not fully exploit the propertie…

Natural Language Understanding