You need a custom version of the tokenizers library to use this tokenizer.
To install this custom version you can:
pip install transformers
git clone https://github.com/huggingface/tokenizers.git
cd tokenizers
git checkout bigscience_fork
cd bindings/python
pip install setuptools_rust
pip install -e .
and then to load it, do:
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("bigscience-catalogue-data-dev/byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles")