Views
No views yet
rerank-multilingual-v2.0 tokenizer1from transformers import AutoTokenizer
2
3tokenizer = AutoTokenizer.from_pretrained("CohereLabs/rerank-multilingual-v2.0")
4text = "Hello World, this is my input string!"
5enc = tokenizer(text)
6print("Encoded input:")
7print(enc)
8
9inv_vocab = {v: k for k, v in tokenizer.vocab.items()}
10tokens = [inv_vocab[token_id] for token_id in enc['input_ids']]
11print("Tokens:")
12print(tokens)
13
14number_of_tokens = len(enc['input_ids'])
15print("Number of tokens:", number_of_tokens)