Exercises
LM-C15-C-001
How many ordered recurrent steps are needed for 9 tokens?
Compute it first, then check your number.
LM-C15-C-002
If hidden size is fixed at 128, how many numbers are in the hidden state?
Compute it first, then check your number.
LM-C15-C-003
If a position reads from 5 earlier positions, how many earlier positions are included?
Compute it first, then check your number.
LM-C15-C-004
What is the largest of 0.1, 0.7, and 0.2, multiplied by 10?
Compute it first, then check your number.
LM-C15-C-005
Do attention weights for one distribution often sum to 1? Answer 1 for yes or
0 for no.
Compute it first, then check your number.