Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

THUDM/icetk

A unified tokenization tool for Images, Chinese and English.

Owner
THUDM (organization)
Stars
Stars: 153
Forks
Forks: 16
Language
Python
License
None
Created
2021
Topics
tokenizationtransformer
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by THUDM

All 47 repos by THUDM

Nearby in Python

All Python repos