Timeline for Attention: Isn't it redundant to apply a linear layer to both the keys and values?
Current License: CC BY-SA 4.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 17, 2022 at 22:43 | vote | accept | Tom Huntington | ||
| Apr 12, 2022 at 0:30 | history | answered | Tom Huntington | CC BY-SA 4.0 |