paper-with-me

Papers

TorchScale: Transformers at Scale

2022-11-23 · Shuming Ma, Hongyu Wang, Shaohan Huang, Wenhui Wang, Zewen Chi, Li Dong, Alon Benhaim, Barun Patra, Vishrav Chaudhary, Xia Song, Furu Wei

Large Transformers have achieved state-of-the-art performance across many tasks. Most open-source libraries on scaling Transformers focus on improving training or inference with better parallelization. In this work, we present TorchScale, an open-source toolkit that allows researchers and developers to scale up Transformers efficiently and effectively. TorchScale has the implementation of several modeling techniques, which can improve modeling generality and capability, as well as training stability and efficiency. Experimental results on language modeling and neural machine translation demonstrate that TorchScale can successfully scale Transformers to different sizes without tears. The library is available at https://aka.ms/torchscale.

📄 PDF Abstract BibTeX arXiv:2211.13184

Code (1)

microsoft/torchscale 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

Co-Scale Conv-Attentional Image Transformers

2021-04-13 · ICCV 2021 10 · Weijian Xu, Yifan Xu, Tyler Chang, Zhuowen Tu

In this paper, we present Co-scale conv-attentional image Transformers (CoaT), a Transformer-based image classifier equipped with co-scale and conv-attentional mechanisms. First, the co-scale mechanism maintains the inte…

Instance Segmentationobject-detectionObject DetectionSemantic Segmentation

Multiscale Vision Transformers

2021-04-22 · ICCV 2021 10 · Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li 외

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-res…

Action ClassificationAction Recognitionimage-classificationImage Classification+1

Adversarial Robustness of In-Context Learning in Transformers for Linear Regression

2024-11-07 · Usman Anwar, Johannes von Oswald, Louis Kirsch, David Krueger 외

Transformers have demonstrated remarkable in-context learning capabilities across various domains, including statistical learning tasks. While previous work has shown that transformers can implement common learning algor…

Adversarial RobustnessIn-Context Learningregression

CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention

2021-07-31 · ICLR 2022 4 · Wenxiao Wang, Lu Yao, Long Chen, Binbin Lin 외

Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is …

image-classificationImage ClassificationInstance Segmentationobject-detection+3

Scalable Transformers for Neural Machine Translation

2021-06-04 · Peng Gao, Shijie Geng, Yu Qiao, Xiaogang Wang 외

Transformer has been widely adopted in Neural Machine Translation (NMT) because of its large capacity and parallel training of sequence generation. However, the deployment of Transformer is challenging because different …

Machine TranslationNMTTranslation