mirror of
https://github.com/mii443/tokenizers.git
synced 2025-08-23 16:49:27 +00:00
pyo3 v0.18 migration (#1173)
* pyo v0.18 migration * Fix formatting issues of black
This commit is contained in:
@ -11,6 +11,7 @@ bpe_tokenizer.normalizer = normalizers.Lowercase()
|
||||
# Initialize a dataset
|
||||
dataset = datasets.load_dataset("wikitext", "wikitext-103-raw-v1")
|
||||
|
||||
|
||||
# Build an iterator over this dataset
|
||||
def batch_iterator():
|
||||
batch_length = 1000
|
||||
|
Reference in New Issue
Block a user