Command-nightly

from tokenizers import Tokenizer

tokenizer = Tokenizer.from_pretrained("CohereLabs/Command-nightly")
text = "Hellö World, this is my input string!"
enc = tokenizer.encode(text)
print("Encoded input:")
print(enc)

inv_vocab = {v: k for k, v in tokenizer.get_vocab().items()}
tokens = [inv_vocab[token_id] for token_id in enc.ids]
print("Tokens:")
print(tokens)

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