mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-11 14:21:41 +08:00

History

rasbt 87fcfd9245 mha variants		2024-03-06 08:30:32 -06:00
..
01_main-chapter-code	mha variants	2024-03-06 08:30:32 -06:00
02_bonus_efficient-multihead-attention	mha variants	2024-03-06 08:30:32 -06:00
README.md	mha variants	2024-03-06 08:30:32 -06:00

Chapter 3: Coding Attention Mechanisms

01_main-chapter-code contains the main chapter code.
02_bonus_efficient-multihead-attention implements and compares different implementation variants of multihead-attention