Formal Algorithms for Transformers

It covers what Transformers are (Section 3 Transformers and Typical Tasks 3 6), how they are trained (Section 7), what 4 Tokenization: How Text is Represented 4 they're used for (Section 3), their key architectural 5 Architectural Components 4 components (Section 5), tokenization (Section 6 Transformer Architectures 7 4), and a preview of practical considerations 7 Transformer Training and Inference 8 8 Practical Considerations 9 (Section 8) and the most prominent models.