2 个仓库
Awesome GitHub RepositoriesEncoder-Decoder Transformers
Transformer architectures that utilize a bidirectional encoder to process inputs and an autoregressive decoder to generate outputs.
Distinct from Encoder-Decoder Generation Methods: The candidates are either vision-specific or overly narrow; this covers the general NLP encoder-decoder architecture.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Encoder-Decoder Transformers. Refine with filters or upvote what's useful.
Awesome Encoder-Decoder Transformers GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- google-research/text-to-text-transfer-transformer
google-research/text-to-text-transfer-transformer
6,528在 GitHub 上查看这是一个机器学习框架，用于将多样化的自然语言处理任务视为统一的文本到文本问题。它提供了一个用于预训练和微调大规模 Transformer 模型的工具包，利用一种将输入和输出都格式化为原始文本序列的系统。 该框架的特色在于其分布式训练系统，该系统使用基于网格的策略跨多个 TPU 核心扩展模型权重和训练批次。它通过使用可配置的混合率将多样化的数据集组合成单一训练流来支持多任务学习，从而允许单个模型处理各种语言任务。 该系统涵盖了广泛的功能，包括编码器-解码器架构、用于文本生成的束搜索解码以及迁移学习工作流。它包括用于 NLP 数据集准备、模型性能评估以及导出训练检查点以进行生产服务的实用程序。 该库支持加载各种大小的预训练模型检查点以加速开发。
Provides a transformer architecture featuring a bidirectional encoder and an autoregressive decoder for sequence-to-sequence tasks.
Python - rasbt/machine-learning-book
rasbt/machine-learning-book
5,239在 GitHub 上查看This project is a comprehensive machine learning educational resource and tutorial series delivered as a collection of interactive Jupyter Notebooks. It provides practical Python implementations for the end-to-end machine learning lifecycle, covering supervised and unsupervised learning, deep learning, and reinforcement learning. The resource distinguishes itself by providing detailed implementation guides for complex architectures, including transformers, generative adversarial networks, and convolutional neural networks. It also features specialized courseware for developing reinforcement l
Implements transformer architectures using encoder-decoder structures for processing and generating sequential information.
Jupyter Notebook
