Transformer 解釋器：互動式學習文本生成模型

Transformer Explainer: Interactive Learning of Text-Generative Models

August 8, 2024

作者: Aeree Cho, Grace C. Kim, Alexander Karpekov, Alec Helbling, Zijie J. Wang, Seongmin Lee, Benjamin Hoover, Duen Horng Chau

cs.AI

摘要

Transformer 已經徹底改變了機器學習，然而其內部運作對許多人來說仍然是不透明的。我們提出了 Transformer Explainer，這是一個互動式可視化工具，專為非專家設計，讓他們通過 GPT-2 模型來學習有關 Transformer。我們的工具幫助使用者理解複雜的 Transformer 概念，通過整合模型概覽並實現在數學操作和模型結構的抽象層級之間平滑過渡。它在使用者的瀏覽器中本地運行一個即時的 GPT-2 實例，讓使用者可以嘗試他們自己的輸入，並實時觀察 Transformer 的內部組件和參數如何一起工作來預測下一個 token。我們的工具無需安裝或特殊硬體，擴大了公眾對現代生成式人工智慧技術的教育訪問。我們的開源工具可在 https://poloclub.github.io/transformer-explainer/ 上找到。視頻演示可在 https://youtu.be/ECR4oAwocjs 上觀看。

English

Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our tool helps users understand complex Transformer concepts by integrating a model overview and enabling smooth transitions across abstraction levels of mathematical operations and model structures. It runs a live GPT-2 instance locally in the user's browser, empowering users to experiment with their own input and observe in real-time how the internal components and parameters of the Transformer work together to predict the next tokens. Our tool requires no installation or special hardware, broadening the public's education access to modern generative AI techniques. Our open-sourced tool is available at https://poloclub.github.io/transformer-explainer/. A video demo is available at https://youtu.be/ECR4oAwocjs.