You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
363 B
363 B
| title | status | type | priority | created_at | updated_at | parent |
|---|---|---|---|---|---|---|
| Write §5: Self-attention — queries, keys, and values | completed | task | normal | 2026-03-13T22:01:53Z | 2026-03-16T02:30:26Z | edu-u2w7 |
Derive the scaled dot-product attention formula from first principles. Single-head attention only (GPT-1 simplicity). Causal masking explained here.