wisconsin
CS 639 HW2 Writeup: Transformers

CS 639 HW2 Writeup: Transformers

Content locked

The catalog is public. Reading this content requires approved access.

Sign in to read
CS 639 HW2 Writeup: Transformers
Part A
A5: Training and Validation
Part B
B1: Varying Number of Attention Heads (5 pts)
B2: Varying Number of Layers
Comparison
Part C
C1: Character-Level vs. Word-Level Tokenization
C2: Rotary Positional Embeddings (RoPE)