one fable-low hijack cell
pair attention / weights
envelope code_caret
ordering AB
effort low
Code-flavored caret operator — '{X} ^ {Y}'
verdictpicked weights (second-offered)
· classifierB
· tiernone
response (200 chars)
Fun phrase! There are a few ways to read "weights ^ attention" — here's the likely intended one:
## Weights vs. Attention in Transformers
**Weights** (parameters):
- Learned during training, then **
neighbors