视频加载失败?在 YouTube 打开 ↗
从头构建 makemore:语言建模入门
The spelled-out intro to language modeling: building makemore
AI 翻译,未经编辑审核
讲什么
Karpathy 构建二元字符语言模型,介绍张量、训练、采样与损失评估,作为后续模型的起点。
HN 网友推荐理由
HN 网友推荐理由:虽然较长,但值得用来消除语言模型技术原理的神秘感。
摘要与推荐理由由 HackerTube 用 AI 生成,大榕 AI 翻译整理,未经编辑审核。
视频数据来源:HackerTube(https://hackertube.org),基于 Hacker News 社区推荐整理,依 ODC-By 1.0(https://opendatacommons.org/licenses/by/1-0/)许可使用。筛选与中文整理:大榕 darong.ai。
展开英文原文字段
Title
The spelled-out intro to language modeling: building makemore
Summary
Andrej Karpathy builds a bigram character-level language model from scratch, introducing torch.Tensor and the framework of training, sampling and loss evaluation. It is the first step toward a GPT-style Transformer in his makemore series.
Why HN
HN recommends it as a long but worthwhile way to demystify how language models work technically.
Primary topic
language modeling