Skip to content

gguf-py : fix TemplateProcessing pair when bos/eos is missing #14312

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
merged 1 commit into from
Jun 21, 2025
Merged

gguf-py : fix TemplateProcessing pair when bos/eos is missing #14312

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
6 changes: 3 additions & 3 deletions gguf-py/gguf/vocab.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -201,9 +201,9 @@ def _try_load_from_tokenizer_json(self, path: Path) -> bool:
if special_last != special_eos:
logger.warning(f'Unknown trailing special token {special_last!r} in TemplateProcessing<single>')
if tmpl_pair:
seq_start = 1 if tmpl_pair[0].get('SpecialToken', {}).get('id') == special_first else 0
seq_stop = -1 if tmpl_pair[-1].get('SpecialToken', {}).get('id') == special_last else None
if seq_start == 0 or seq_stop is None:
seq_start = 1 if special_first and tmpl_pair[0].get('SpecialToken', {}).get('id') == special_first else 0
seq_stop = -1 if special_last and tmpl_pair[-1].get('SpecialToken', {}).get('id') == special_last else None
if (special_first and seq_start == 0) or (special_last and seq_stop is None):
logger.warning('TemplateProcessing<single> leading/trailing special tokens do not match TemplateProcessing<pair>')
if tmpl_pair := tmpl_pair[slice(seq_start, seq_stop)]:
tmpl_a = tmpl_pair[0].get('Sequence', {}).get('id')
Expand Down