Byte Pair Encoding
Concept
A data compression technique adapted for language models, used to construct vocabularies tailored to data by merging frequent byte pairs.
Mentioned in 2 videos
Save the 2 videos on Byte Pair Encoding to your own pod.
Sign up free to keep building your knowledge base on Byte Pair Encoding as more episodes are added.
Videos Mentioning Byte Pair Encoding
Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 1: Overview, Tokenization
Stanford Online
A data compression technique adapted for language models, used to construct vocabularies tailored to data by merging frequent byte pairs.
Stanford CS229 Machine Learning | Spring 2026 | Lecture 14: Transformers, In-Context Learning
Stanford Online
The algorithm used for tokenization, which identifies frequent subwords to build a vocabulary.