B

Byte Pair Encoding (BPE)

Tool / ProductMentioned in 1 video

Tokenization algorithm (merging common byte/byte-pair sequences) used to build large vocabularies (~100k tokens).

Videos Mentioning Byte Pair Encoding (BPE)

Deep Dive into LLMs like ChatGPT

Deep Dive into LLMs like ChatGPT

Andrej Karpathy

Tokenization algorithm (merging common byte/byte-pair sequences) used to build large vocabularies (~100k tokens).