This project implements a small Transformer model trained to perform modular addition: $(a + b) \pmod{100}$. It serves as a classic experiment to demonstrate Grokking and the emergence of ...
# Given two numbers a and b, find the sum of a and b. Since the sum can be very large, find the sum modulo 109+7. # You don't need to read input or print anything. Your task is to complete the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results