Learning Transformer
Attention, one step at a time
Free · In-App Purchases · Designed for iPad. Not verified for macOS.
No training, no black box. Every weight was set by hand so it can be read in one line, and every number on screen is computed while you look at it.
A Transformer, built by hand and shown one step at a time.
Twenty-three screens follow "Attention Is All You Need" (Vaswani et al., 2017) in the paper's own order: a word becoming numbers, the three vectors, the scores, the softmax, four heads merged into one, the mask, the second attention, and the loop that writes one word at a time.
What this is not: a trained model. Every weight here was set by hand, so that each one can be read in a single line. Nine numbers stand for a word instead of 512. One encoder layer and one decoder layer instead of six of each. Four heads, four words of vocabulary, one short sentence.
What it is: the paper's arithmetic at a size you can check by hand. Every number on every screen is computed while you look at it — no videos, no quizzes, no account, no network.
Steps 1 to 10 are free. Steps 11 to 23 are one purchase, made once and kept.
Ratings & Reviews
- This app has not received enough ratings or reviews to display an overview.
The developer, Sungjun Kim, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .
Data Not Collected
The developer does not collect any data from this app.
Accessibility
The developer has not yet indicated which accessibility features this app supports. Learn More
Information
- Provider
- Sungjun Kim
- Size
- 769 KB
- Category
- Education
- Compatibility
Requires iOS 17.0 or later.
- iPhone
Requires iOS 17.0 or later. - iPad
Requires iPadOS 17.0 or later. - Mac
Requires macOS 14.0 or later and a Mac with Apple M1 chip or later.
- iPhone
- Languages
- English
- Age Rating
4+
- 4+
- In-App Purchases
Yes
- the decoder USD 4.99
- Copyright
- © Sungjun Kim