TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

A Visual Intro to Large Language Models

50 点作者 jalammar超过 3 年前

1 comment

jalammar超过 3 年前
Hi HN,<p>This is the first in a series of articles I&#x27;m writing to introduce devs to practical applications of large NLP language models (for text generations like GPT and for language understanding like BERT).<p>I have been connecting the dots between the capabilities of these models and their business application. I still believe we&#x27;re in the beginning of grasping the amount of potential value we can extract from these models. Happy to get to share these as I learn them from my exposure to the problem space.<p>Some of the key visual language I&#x27;m aiming to simplify is that of &quot;prompts&quot; and their use to shape model output (leading to practical applications). In this post, a key visual is [1] which shows an example of a summarization prompt and [2] showing a high-level process of &quot;prompt engineering&quot;.<p>Would appreciate your feedback!<p>[1] <a href="https:&#x2F;&#x2F;docs.cohere.ai&#x2F;img&#x2F;intro-llms&#x2F;language-model-prompt.png" rel="nofollow">https:&#x2F;&#x2F;docs.cohere.ai&#x2F;img&#x2F;intro-llms&#x2F;language-model-prompt....</a> [2] <a href="https:&#x2F;&#x2F;docs.cohere.ai&#x2F;img&#x2F;intro-llms&#x2F;prompt-engineering-and-finetuning.png" rel="nofollow">https:&#x2F;&#x2F;docs.cohere.ai&#x2F;img&#x2F;intro-llms&#x2F;prompt-engineering-and...</a>
评论 #29338817 未加载