| 📄 | 01_cover.md | 657 B |
| 📄 | 02_why_it_matters.md | 640 B |
| 📄 | 03_sequence_evolution.md | 673 B |
| 📄 | 04_rnn_cnn_limits.md | 562 B |
| 📄 | 05_architecture_overview.md | 746 B |
| 📄 | 06_encoder_decoder.md | 706 B |
| 📄 | 07_scaled_dot_product.md | 645 B |
| 📄 | 08_multi_head_attention.md | 630 B |
| 📄 | 09_three_uses.md | 732 B |
| 📄 | 10_ffn_residual_layernorm.md | 631 B |
| 📄 | 11_positional_encoding.md | 629 B |
| 📄 | 12_complexity_table.md | 641 B |
| 📄 | 13_training_setup.md | 664 B |
| 📄 | 14_results.md | 597 B |
| 📄 | 15_ablations.md | 728 B |
| 📄 | 16_conclusion.md | 601 B |
| 📄 | total.md | 10.7 KB |