Short Course Q&A Attention in Transformers: Concepts and Code in Py
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
|
Why do we use square root of key dimension for scaling?
|
|
2 | 33 | February 27, 2025 |
|
The Matrix Math for self-attention
|
|
4 | 56 | February 22, 2025 |
|
In class MaskedSelfAttention -- don't understand python statement
|
|
6 | 62 | February 16, 2025 |