基于 PyTorch 的《Attention is All You Need》中 Transformer 模型的实现。
attention-is-all-you-need 开源项目推荐(368 个)
attention-is-all-you-need 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 368 个仓库Transformer的TensorFlow实现:注意力就是你所需要的一切
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Learn LLM internals step by step - from tokenization to attention to inference optimization.
Attention is all you need implementation
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.
list of efficient attention modules
面向语言理解的深度双向 Transformer 预训练:预训练 TextCNN
A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
Keras+TensorFlow 实现变换器:注意力就是你所需要的全部
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.
A Benchmark of Text Classification in PyTorch
Pytorch 实现的“注意力就是你所需要的全部”和“机器翻译加权变换器网络”
Neural Machine Translation with Keras
关于《注意力就是你所需要的》视频笔记(https://www.youtube.com/watch?v=bCz4OMemCcA)
关注就是你所需要的全部 |PyTorch 变形金刚教程
Implementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/attention-is-all-you-need。
- 该话题在 GitHub 上共有 368 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 3.1 万 Star,覆盖 2 种主要语言,数据更新于 2026-11-06。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。