Tokenization & Embedding Lecture 2 01 Tokenization 02 Text → Token IDs → Embedding 03 Subword 04 Unicode & Normalization 05 Byte-Pair Encoding 06 WordPiece · Unigram LM · SentencePiece 07 Vocabulary Size 08 Numbers & Code 09 Fertility & Token Tax 10 Tokenizer Transfer 11 Glitch Tokens 12 Special Tokens & Chat Templates 13 Template Mismatch 14 Any-to-Any Models 15 Embedding Table 16 Weight Tying & LM Head 17 Static → Contextual Embeddings 18 Text Embedding 19 Contrastive Training 20 Decoder-Based Text Embedding 21 Matryoshka Representation Learning 22 M3DocDep Chunking 23 MRL Evaluation