Skip to content

Sort unique_no_split_tokens to make it deterministic #6461

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lhoestq merged 3 commits into from
Aug 14, 2020
Merged

Sort unique_no_split_tokens to make it deterministic #6461

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b7dcfc0
change unique_no_split_tokens's type to set
lhoestq Aug 13, 2020
b3aa139
use sorted list instead of set
lhoestq Aug 13, 2020
dfb7549
style
lhoestq Aug 13, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions src/transformers/tokenization_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
import logging
import re
import unicodedata
from typing import Any, Dict, List, Optional, Tuple, Union
from typing import Any, Dict, List, Optional, Set, Tuple, Union

from .file_utils import add_end_docstrings
from .tokenization_utils_base import (
Expand Down Expand Up @@ -118,7 +118,7 @@ def __init__(self, **kwargs):
# until the serialization of Fast tokenizers is updated
self.added_tokens_encoder: Dict[str, int] = {}
self.added_tokens_decoder: Dict[int, str] = {}
self.unique_no_split_tokens: List[str] = []
self.unique_no_split_tokens: Set[str] = set()

@property
def is_fast(self) -> bool:
Expand Down Expand Up @@ -207,10 +207,10 @@ def _add_tokens(self, new_tokens: Union[List[str], List[AddedToken]], special_to

# Make sure we don't split on any special tokens (even they were already in the vocab before e.g. for Albert)
if special_tokens:
self.unique_no_split_tokens = list(set(self.unique_no_split_tokens).union(set(new_tokens)))
self.unique_no_split_tokens = set(self.unique_no_split_tokens).union(set(new_tokens))
else:
# Or on the newly added tokens
self.unique_no_split_tokens = list(set(self.unique_no_split_tokens).union(set(tokens_to_add)))
self.unique_no_split_tokens = set(self.unique_no_split_tokens).union(set(tokens_to_add))

return len(tokens_to_add)

Expand Down Expand Up @@ -347,7 +347,7 @@ def split_on_tokens(tok_list, text):
)

no_split_token = self.unique_no_split_tokens
tokenized_text = split_on_tokens(no_split_token, text)
tokenized_text = split_on_tokens(list(no_split_token), text)
return tokenized_text

def _tokenize(self, text, **kwargs):
Expand Down