Gemma's Tokenizer fails to split on spaces

[vasqu]

Preface

This is related to #29617, similar issue as described in there so this is kind of a placeholder. Should be fixed by #28881.

Who can help?

@ArthurZucker

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('google/gemma-7b', use_auth=True)
sentence = 'Sampel to demonstrate the issue'

input_encoding = tokenizer(sentence, add_special_tokens=True)
tokens = input_encoding.tokens()
word_ids = input_encoding.word_ids()

print(f'Tokens produced: {tokens}\nReferenced word ids: {word_ids}')

Expected behavior

Correct split(s) assigned.