Model techniques map
Techniquesdata curationtokenization

specific method · filed under data curation

o200k_harmony tokenizer

A tokenizer using the o200k_harmony token vocabulary.

Also called o200k_harmony Byte Pair Encoding tokenizer.

sources
2
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

Across all training stages, we utilize our o200k_harmony tokenizer

usedmodel architecturein gpt-oss-120b and gpt-oss-20bOpenAI

They are part of a new token vocabulary called o200k_harmony, which landed in OpenAI’s tiktoken tokenizer library this morning.

usedsoftware implementationin openai/harmonyOpenAI

Filed alongside

Other methods under data curation :: tokenization.