15 Drafts
·
163,814 Words
·
2 Humanized
·
13 In Review
Chapter 1
Introduction
10,740 words
Draft
Chapter 2
Mathematical Foundations
10,759 words
Humanized
Chapter 3
Classical Language Models
8,514 words
Humanized
Chapter 4
Word Representations
9,613 words
Draft
Chapter 5
Sequence Models
11,081 words
Draft
Chapter 6
The Attention Revolution
10,902 words
Draft
Chapter 7
Sequence-to-Sequence and Decoding
10,519 words
Draft
Chapter 8
The Transformer Architecture
12,877 words
Draft
Chapter 9
Pre-training Paradigms
13,529 words
Draft
Chapter 10
Tokenization and Data at Scale
9,990 words
Draft
Chapter 11
Scaling Laws and Emergent Abilities
12,334 words
Draft
Chapter 12
Alignment: RLHF, DPO, Safety
11,220 words
Draft
Chapter 13
In-Context Learning, Prompting, and Reasoning
12,595 words
Draft
Chapter 14
Retrieval, Agents, and Multimodal Models
11,107 words
Draft
Chapter 15
Ethics, Society, and the Future
8,034 words
Draft