English
Related papers

Related papers: MKQ-BERT: Quantized BERT with 4-bits Weights and A…

200 papers

Transformer-based language models are applied to a wide range of applications in natural language processing. However, they are inefficient and difficult to deploy. In recent years, many compression algorithms have been proposed to increase…

Computation and Language · Computer Science 2021-11-11 Ofir Zafrir , Ariel Larey , Guy Boudoukh , Haihao Shen , Moshe Wasserblat

Recent advances in self-supervised learning and the Transformer architecture have significantly improved natural language processing (NLP), achieving remarkably low perplexity. However, the growing size of NLP models introduces a memory…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-04-02 Gunho Park , Baeseong Park , Minsub Kim , Sungjae Lee , Jeonghoon Kim , Beomseok Kwon , Se Jung Kwon , Byeongwook Kim , Youngjoo Lee , Dongsoo Lee

Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ…

Computation and Language · Computer Science 2019-09-23 Alham Fikri Aji , Kenneth Heafield

Large-scale pre-trained language models such as BERT have contributed significantly to the development of NLP. However, those models require large computational resources, making it difficult to be applied to mobile devices where computing…

Computation and Language · Computer Science 2023-08-02 Weixin Wu , Hankz Hankui Zhuo

Natural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from heavy model sizes and high latency such that they cannot be…

Computation and Language · Computer Science 2020-04-16 Zhiqing Sun , Hongkun Yu , Xiaodan Song , Renjie Liu , Yiming Yang , Denny Zhou

Existing pre-trained language models (PLMs) are often computationally expensive in inference, making them impractical in various resource-limited real-world applications. To address this issue, we propose a dynamic token reduction approach…

Computation and Language · Computer Science 2021-05-26 Deming Ye , Yankai Lin , Yufei Huang , Maosong Sun

Recently, pre-trained language models like BERT have shown promising performance on multiple natural language processing tasks. However, the application of these models has been limited due to their huge size. To reduce its size, a popular…

Computation and Language · Computer Science 2020-10-15 Zihan Zhao , Yuncong Liu , Lu Chen , Qi Liu , Rao Ma , Kai Yu

Transformers \citep{vaswani2017attention} have gradually become a key component for many state-of-the-art natural language representation models. A recent Transformer based model- BERT \citep{devlin2018bert} achieved state-of-the-art…

Computation and Language · Computer Science 2020-05-15 Ashish Khetan , Zohar Karnin

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional…

Computation and Language · Computer Science 2019-05-28 Jacob Devlin , Ming-Wei Chang , Kenton Lee , Kristina Toutanova

Pre-trained language models like BERT have proven to be highly performant. However, they are often computationally expensive in many practical scenarios, for such heavy models can hardly be readily implemented with limited resources. To…

Computation and Language · Computer Science 2020-04-30 Weijie Liu , Peng Zhou , Zhe Zhao , Zhiruo Wang , Haotang Deng , Qi Ju

Pre-trained language models have shown remarkable results on various NLP tasks. Nevertheless, due to their bulky size and slow inference speed, it is hard to deploy them on edge devices. In this paper, we have a critical insight that…

Computation and Language · Computer Science 2021-09-17 Chenhe Dong , Guangrun Wang , Hang Xu , Jiefeng Peng , Xiaozhe Ren , Xiaodan Liang

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding…

Machine Learning · Computer Science 2024-08-01 Ying Zhang , Peng Zhang , Mincong Huang , Jingyang Xiang , Yujie Wang , Chao Wang , Yineng Zhang , Lei Yu , Chuan Liu , Wei Lin

Large language models (LLMs) have revolutionized language processing, delivering outstanding results across multiple applications. However, deploying LLMs on edge devices poses several challenges with respect to memory, energy, and compute…

Computation and Language · Computer Science 2024-10-07 Fuwen Tan , Royson Lee , Łukasz Dudziak , Shell Xu Hu , Sourav Bhattacharya , Timothy Hospedales , Georgios Tzimiropoulos , Brais Martinez

We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both weights and activations and apply Quantization Aware Training…

Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs while keeping performance degradation at an acceptable level. However, the optimal choice of quantization format and bit-width…

Machine Learning · Computer Science 2026-02-18 Sohir Maskey , Constantin Eichenberg , Johannes Messner , Douglas Orr

How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements. In this work, we present an…

Computation and Language · Computer Science 2022-06-07 Zhewei Yao , Reza Yazdani Aminabadi , Minjia Zhang , Xiaoxia Wu , Conglong Li , Yuxiong He

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut

The development of over-parameterized pre-trained language models has made a significant contribution toward the success of natural language processing. While over-parameterization of these models is the key to their generalization power,…

Computation and Language · Computer Science 2021-09-15 Marzieh S. Tahaei , Ella Charlaix , Vahid Partovi Nia , Ali Ghodsi , Mehdi Rezagholizadeh

The upscaling of Large Language Models (LLMs) has yielded impressive advances in natural language processing, yet it also poses significant deployment challenges. Weight quantization has emerged as a widely embraced solution to reduce…

Computation and Language · Computer Science 2024-02-19 Dayou Du , Yijia Zhang , Shijie Cao , Jiaqi Guo , Ting Cao , Xiaowen Chu , Ningyi Xu

Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…

Computation and Language · Computer Science 2024-07-04 Ying Zhang , Ziheng Yang , Shufan Ji