pytorch/examples

word_language_model with torch.nn.modules.transformer

Open

#1,112 创建于 2023年2月9日

在 GitHub 查看
 (3 评论) (0 反应) (0 负责人)Python (21,634 star) (9,429 fork)batch import
docsgood first issuenlp

描述

The torch.nn.modules.transformer documentation says the word_language_model example in this repo is an example of its use. But it seems to instead DIY a transformer and uses that instead. Is this intentional? I would offer my help to write it for torch.nn.modules.transformer but I'm here to learn how to use it.

贡献者指南

技术栈
python
领域
machine learningdocumentation
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
half day
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
PythonPyTorch basicsTransformer architecture
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
60
研究方向
Examine the existing word language model example in the pytorch/examples repository (likely under examples/word language model). Compare the current DIY transformer implementation with the official torch.nn.Transformer module. Review the documentation for torch.nn.modules.transformer to understand how to integrate it. Check the issue comments for any additional context or maintainer feedback.