Skip to content

Fix ByteLevel alphabet missing when Sequence pretokenizer is used #33556

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
itazap merged 2 commits into from
Sep 24, 2024
Merged

Fix ByteLevel alphabet missing when Sequence pretokenizer is used #33556

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e8c6a40
Fix ByteLevel alphabet missing when Sequence pretokenizer is used
umarbutler Sep 18, 2024
f631ca3
Fixed formatting with `ruff`.
umarbutler Sep 22, 2024
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
7 changes: 6 additions & 1 deletion src/transformers/tokenization_utils_fast.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -824,7 +824,12 @@ def train_new_from_iterator(
kwargs["end_of_word_suffix"] = tokenizer_json["model"]["end_of_word_suffix"]
if tokenizer_json["model"]["type"] == "Unigram" and unk_token is not None:
kwargs["unk_token"] = unk_token
if tokenizer_json["pre_tokenizer"] is not None and tokenizer_json["pre_tokenizer"]["type"] == "ByteLevel":
if tokenizer_json["pre_tokenizer"] is not None \
and tokenizer_json["pre_tokenizer"]["type"] == "ByteLevel" \
or tokenizer_json["pre_tokenizer"]["type"] == "Sequence" and \
"pretokenizers" in tokenizer_json["pre_tokenizer"] and \
any(pretokenizer["type"] == "ByteLevel"
for pretokenizer in tokenizer_json["pre_tokenizer"]["pretokenizers"]):
kwargs["initial_alphabet"] = pre_tokenizers_fast.ByteLevel.alphabet()

trainer_class = MODEL_TO_TRAINER_MAPPING[tokenizer_json["model"]["type"]]
Expand Down