Glossary · Phase 4 · Deep learning
d_model
The width of a transformer: how many numbers stand for each token as it passes through the layers.
Try it now
No calculation, just a lookup. What makes it useful is that training learns the table's contents.
Learn it properly
Embedding layers · Learned lookup tables that turn tokens into vectors. About 30 minutes.
Other terms from the same lesson
- embedding layer: A lookup table that gives each word or token its own learned list of numbers.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.