Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Spaces:
yhavinga
/
dutch-tokenizer-arena
like
6
Running
App
Files
Files
Community
1
11379e2
dutch-tokenizer-arena
/
vocab
/
chinese_llama2
/
demo.py
eson
add more tokenizers
f4973d4
8 months ago
raw
Copy download link
history
blame
No virus
132 Bytes
from
vocab.chinese_llama2
import
tokenizer
encoding = tokenizer.encode(
"<s>开始</s>站位符<pad>试试<unk>"
)
print
(encoding)