Model techniques map
Techniquesdata curationtokenization

specific method · filed under data curation

SentencePiece tokenizer

A SentencePiece tokenizer described as using split digits, preserved whitespace, and byte-level encodings.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

We use the same tokenizer as Gemini Team [2025] that is, a SentencePiece tokenizer [Kudo and Richardson, 2018] with split digits, preserved whitespace, and byte-level encodings.

useddata curationin Gemma 4Google DeepMind

Filed alongside

Other methods under data curation :: tokenization.