English
Related papers

Related papers: Megrez2 Technical Report

200 papers

The advent of the transformer has sparked a quick growth in the size of language models, far outpacing hardware improvements. (Dense) transformers are expected to reach the trillion-parameter scale in the near future, for which training…

Machine Learning · Computer Science 2021-06-08 Joel Lamy-Poirier

Recent work in language modeling demonstrates that training large transformer models advances the state of the art in Natural Language Processing applications. However, very large models can be quite difficult to train due to memory…

Computation and Language · Computer Science 2020-03-17 Mohammad Shoeybi , Mostofa Patwary , Raul Puri , Patrick LeGresley , Jared Casper , Bryan Catanzaro

In this paper, we provide a fine-grain machine learning-based method, PerfNetV2, which improves the accuracy of our previous work for modeling the neural network performance on a variety of GPU accelerators. Given an application, the…

Machine Learning · Computer Science 2020-12-02 Chuan-Chi Wang , Ying-Chiao Liao , Ming-Chang Kao , Wen-Yew Liang , Shih-Hao Hung

Large Language Models (LLMs) remain heavily centered on English, with limited performance in low-resource languages. Existing adaptation approaches, such as continual pre-training, demand significant computational resources. In the case of…

Computation and Language · Computer Science 2026-03-31 Eneko Valero , Maria Ribalta i Albado , Oscar Sainz , Naiara Perez , German Rigau

Recently, prefix-tuning has gained increasing attention as a parameter-efficient finetuning method for large-scale pretrained language models. The method keeps the pretrained models fixed and only updates the prefix token parameters for…

Computation and Language · Computer Science 2022-03-22 Zonghan Yang , Yang Liu

We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference. Our method, which we…

Computation and Language · Computer Science 2025-11-27 Dong Dong , Weijie Su

Large language models (LLMs), with their powerful generative capabilities and vast knowledge, empower various tasks in everyday life. However, these abilities are primarily concentrated in high-resource languages, leaving low-resource…

Computation and Language · Computer Science 2024-12-20 Shaolei Zhang , Kehao Zhang , Qingkai Fang , Shoutao Guo , Yan Zhou , Xiaodong Liu , Yang Feng

Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense feed-forward layers, providing dedicated…

Computation and Language · Computer Science 2024-12-23 Vincent-Pierre Berges , Barlas Oğuz , Daniel Haziza , Wen-tau Yih , Luke Zettlemoyer , Gargi Ghosh

While machine learning has emerged in recent years as a useful tool for rapid prediction of materials properties, generating sufficient data to reliably train models without overfitting is still impractical for many applications. Towards…

Materials Science · Physics 2022-07-29 Rees Chang , Yu-Xiong Wang , Elif Ertekin

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation…

Computer Vision and Pattern Recognition · Computer Science 2025-01-16 Jiaqi Huang , Zunnan Xu , Ting Liu , Yong Liu , Haonan Han , Kehong Yuan , Xiu Li

A novel accelerated mobile edge generation (MEG) framework is proposed for generating high-resolution images on mobile devices. Exploiting a large-scale latent diffusion model (LDM) distributed across edge server (ES) and user equipment…

Systems and Control · Electrical Eng. & Systems 2024-08-08 Xiaoxia Xu , Yuanwei Liu , Xidong Mu , Hong Xing , Arumugam Nallanathan

Large Language Models (LLMs) continue to demonstrate superior performance with increasing scale, yet training models with billions to trillions of parameters requires staggering computational resources, e.g. a one-trillion-parameter…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-11 Ajay Navilarekal Rajgopal , Nikolai Solmsdorf

Recently, pre-trained transformer-based architectures have proven to be very efficient at language modeling and understanding, given that they are trained on a large enough corpus. Applications in language generation for Arabic are still…

Computation and Language · Computer Science 2021-03-09 Wissam Antoun , Fady Baly , Hazem Hajj

Continued improvements in machine learning techniques offer exciting new opportunities through the use of larger models and larger training datasets. However, there is a growing need to offer these new capabilities on-board low-powered…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-16 Steven M. Hernandez , Ding Zhao , Shaojin Ding , Antoine Bruguier , Rohit Prabhavalkar , Tara N. Sainath , Yanzhang He , Ian McGraw

Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…

Machine Learning · Computer Science 2025-10-21 Yifei He , Siqi Zeng , Yuzheng Hu , Rui Yang , Tong Zhang , Han Zhao

Large language models are typically trained densely: all parameters are updated with respect to all inputs. This requires synchronization of billions of parameters across thousands of GPUs. We introduce a simple but effective method to…

Computation and Language · Computer Science 2023-03-27 Suchin Gururangan , Margaret Li , Mike Lewis , Weijia Shi , Tim Althoff , Noah A. Smith , Luke Zettlemoyer

Large language models (LLMs), despite strong performance on complex mathematical problems, exhibit systematic limitations in counting tasks. This issue arises from the architectural limits of transformers, where counting is performed across…

Residual transformations enhance the representational depth and expressive power of large language models (LLMs). However, applying static residual transformations across all tokens in auto-regressive generation leads to a suboptimal…

Computation and Language · Computer Science 2025-02-05 Nikhil Bhendawade , Mahyar Najibi , Devang Naik , Irina Belousova

Recent breakthroughs and successful deployment of large language and vision models in a constrained environment predominantly follow a two phase approach. First, large models are trained to achieve peak performance, followed by a model…

Machine Learning · Computer Science 2024-11-22 Hanna Mazzawi , Pranjal Awasthi , Xavi Gonzalvo , Srikumar Ramalingam

Recent large language models (LLM) exhibit sub-optimal performance on low-resource languages, as the training data of these models is usually dominated by English and other high-resource languages. Furthermore, it is challenging to train…

Computation and Language · Computer Science 2023-12-18 Zoltan Csaki , Pian Pawakapan , Urmish Thakker , Qiantong Xu