calpt's picture
Add tokenizer
8420110

Cohere rerank-multilingual-v3.0 tokenizer

This is the tokenizer for the Cohere Rerank Multilingual v3 model.

You can load it with the tokenizers library like this:

from tokenizers import Tokenizer

tokenizer = Tokenizer.from_pretrained("Cohere/rerank-multilingual-v3.0")
text = "Hello World, this is my input string!"
enc = tokenizer.encode(text)
print("Encoded input:")
print(enc.ids)

print("Tokens:")
print(enc.tokens)

number_of_tokens = len(enc.ids)
print("Number of tokens:", number_of_tokens)