rasbt-LLMs-from-scratch/ch03/01_main-chapter-code
2024-04-18 05:56:23 -05:00
..
ch03.ipynb Use dim=-1 for consistency (#122) 2024-04-18 05:56:23 -05:00
exercise-solutions.ipynb Rename variable to context_length to make it easier on readers (#106) 2024-04-04 07:27:41 -05:00
multihead-attention.ipynb Use instance tokenizer (#116) 2024-04-10 21:16:19 -04:00
README.md add and update readme files 2024-02-05 06:51:58 -06:00
small-text-sample.txt use block size variable in positional embedding layer 2023-12-28 19:05:06 +01:00

Chapter 3: Coding Attention Mechanisms

  • ch03.ipynb contains all the code as it appears in the chapter
  • multihead-attention.ipynb is a minimal notebook with the main data loading pipeline implemented in this chapter