Skip to content

Fix Kimi-K2.5 tokenizer regression and _patch_mistral_regex AttributeError #45359

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
ArthurZucker merged 1 commit into from
Apr 13, 2026
Merged

Fix Kimi-K2.5 tokenizer regression and _patch_mistral_regex AttributeError #45359

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 0 additions & 1 deletion src/transformers/models/auto/tokenization_auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -358,7 +358,6 @@
"internvl_chat",
"jamba",
"janus",
"kimi_k25",
"llava",
"llava_next",
"minicpmv",
Expand Down
6 changes: 3 additions & 3 deletions src/transformers/tokenization_utils_tokenizers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1360,11 +1360,11 @@ def is_base_mistral(model_id: str) -> bool:
),
behavior="isolated",
)
current_pretokenizer = tokenizer.backend_tokenizer.pre_tokenizer
current_pretokenizer = tokenizer.pre_tokenizer
# Check if it's already a Sequence
if isinstance(current_pretokenizer, tokenizers.pre_tokenizers.Sequence):
# Replace the first element (the Split pattern)
tokenizer.backend_tokenizer.pre_tokenizer[0] = split_pretokenizer
tokenizer.pre_tokenizer[0] = split_pretokenizer
else:
# Replace Metaspace with ByteLevel when adding Split, as Metaspace(split=False) doesn't
# work correctly with the Split pre-tokenizer and causes spaces to be lost during encoding
Expand All @@ -1374,7 +1374,7 @@ def is_base_mistral(model_id: str) -> bool:
)

# Not a Sequence, so create one with Split + current pretokenizer
tokenizer.backend_tokenizer.pre_tokenizer = tokenizers.pre_tokenizers.Sequence(
tokenizer.pre_tokenizer = tokenizers.pre_tokenizers.Sequence(
[
split_pretokenizer,
current_pretokenizer,
Expand Down
Loading