English
Related papers

Related papers: QuaLA-MiniLM: a Quantized Length Adaptive MiniLM

200 papers

We generalize deep self-attention distillation in MiniLM (Wang et al., 2020) by only using self-attention relation distillation for task-agnostic compression of pretrained Transformers. In particular, we define multi-head self-attention…

Computation and Language · Computer Science 2021-06-29 Wenhui Wang , Hangbo Bao , Shaohan Huang , Li Dong , Furu Wei

Large pre-trained language models such as BERT have shown their effectiveness in various natural language processing tasks. However, the huge parameter size makes them difficult to be deployed in real-time applications that require quick…

Computation and Language · Computer Science 2021-01-25 Daoyuan Chen , Yaliang Li , Minghui Qiu , Zhen Wang , Bofang Li , Bolin Ding , Hongbo Deng , Jun Huang , Wei Lin , Jingren Zhou

To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched. A prominent challenge is to quantize the DNN models into low-bitwidth numbers without significant accuracy…

Machine Learning · Computer Science 2024-02-14 Jiajun Zhou , Jiajun Wu , Yizhao Gao , Yuhao Ding , Chaofan Tao , Boyu Li , Fengbin Tu , Kwang-Ting Cheng , Hayden Kwok-Hay So , Ngai Wong

Leveraging shared learning through Massively Multilingual Models, state-of-the-art machine translation models are often able to adapt to the paucity of data for low-resource languages. However, this performance comes at the cost of…

Computation and Language · Computer Science 2022-11-10 Harshita Diddee , Sandipan Dandapat , Monojit Choudhury , Tanuja Ganu , Kalika Bali

We present our submission to the BabyLM challenge, whose goal was to improve the sample efficiency of language models. We trained an ensemble consisting of a GPT-2 and small LLaMA models on the developmentally-plausible, 10M-word BabyLM…

Computation and Language · Computer Science 2023-10-25 Inar Timiryasov , Jean-Loup Tastet

The pre-training models such as BERT have achieved great results in various natural language processing problems. However, a large number of parameters need significant amounts of memory and the consumption of inference time, which makes it…

Computation and Language · Computer Science 2020-12-15 Hao Fu , Shaojun Zhou , Qihong Yang , Junjie Tang , Guiquan Liu , Kaikui Liu , Xiaolong Li

Model compression methods are used to reduce the computation and energy requirements for Large Language Models (LLMs). Quantization Aware Training (QAT), an effective model compression method, is proposed to reduce performance degradation…

Machine Learning · Computer Science 2024-10-16 He Li , Jianhang Hong , Yuanzhuo Wu , Snehal Adbol , Zonglin Li

Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-13 Sankaran Panchapagesan , Daniel S. Park , Chung-Cheng Chiu , Yuan Shangguan , Qiao Liang , Alexander Gruenstein

The deployment of large language models (LLMs) is frequently hindered by prohibitive memory and computational requirements. While quantization mitigates these bottlenecks, maintaining model fidelity in the sub-1-bit regime remains a…

Machine Learning · Computer Science 2026-02-06 Banseok Lee , Dongkyu Kim , Youngcheon You , Youngmin Kim

Knowledge distillation (KD) has become a widely adopted approach for compressing large language models (LLMs) to reduce computational costs and memory footprints. However, the availability of complex teacher models is a prerequisite for…

Computation and Language · Computer Science 2024-11-27 Yao Fu , Yin Yu , Xiaotian Han , Runchao Li , Xianxuan Long , Haotian Yu , Pan Li

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

We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8-bit integers. Existing methods for quantizing models either modify the training procedure,or they require an…

Computation and Language · Computer Science 2022-11-18 Yousef El-Kurdi , Jerry Quinn , Avirup Sil

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

Computation and Language · Computer Science 2020-10-13 Fahimeh Saleh , Wray Buntine , Gholamreza Haffari

Large language models (LLMs) achieve remarkable performance but demand substantial computational resources, limiting deployment on edge devices and resource-constrained environments. We present TernaryLM, a 132M-parameter transformer…

Computation and Language · Computer Science 2026-03-30 Nisharg Nargund , Priyesh Shukla

Despite the outstanding performance of transformers in both language and vision tasks, the expanding computation and model size have increased the demand for efficient deployment. To address the heavy computation and parameter drawbacks,…

Machine Learning · Computer Science 2024-10-15 Xijie Huang , Zhiqiang Shen , Pingcheng Dong , Kwang-Ting Cheng

Inspired by the power of large language models (LLMs), our research adapts them to quantum federated learning (QFL) to boost efficiency and performance. We propose a federated fine-tuning method that distills an LLM within QFL, allowing…

Machine Learning · Computer Science 2025-05-27 Dev Gurung , Shiva Raj Pokhrel

Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime remains challenging. Existing post-training methods often…

Machine Learning · Computer Science 2026-05-27 Phong Nam Huu Nguyen , Khoi M. Le , Cong-Duy T Nguyen , Anh Tuan Luu , Thong Thanh Nguyen , Tho Quan

The Efficient Adaptive Transformer (EAT) framework unifies three adaptive efficiency techniques - progressive token pruning, sparse attention, and dynamic early exiting - into a single, reproducible architecture for input-adaptive…

Computation and Language · Computer Science 2025-10-16 Jan Miller

Extreme compression, particularly ultra-low bit precision (binary/ternary) quantization, has been proposed to fit large NLP models on resource-constraint devices. However, to preserve the accuracy for such aggressive compression schemes,…

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

Large Language Models (LLMs) have demonstrated outstanding performance across a range of NLP tasks, however, their computational demands hinder their deployment in real-world, resource-constrained environments. This work investigates the…

Computation and Language · Computer Science 2025-07-11 Joyeeta Datta , Niclas Doll , Qusai Ramadan , Zeyd Boukhers
‹ Prev 1 4 5 6 7 8 10 Next ›