Posts

2025-05-15 Kernel Shape in a CNN Audio Model

2025-05-06 One Double RoBERTa, with a Side of Strange

2025-04-29 What's Going On at Layer 5?

2025-04-22 More Attention to Attention

2024-11-08 Paying Attention Part 2

2024-10-31 Paying Attention to Attention

2024-10-07 Audio Tokens Part 18: The Wrap-Up

2024-10-03 Audio Tokens Part 17: All Sane, So Far

2024-10-03 Audio Tokens Part 16: Sanity Checks for Everyone!

2024-09-30 Trees and Language