Skip to content
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.

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

convert : handle tokenizer merges format from transformers 4.45 #9696

Merged
merged 2 commits into from
Oct 3, 2024
Merged
Changes from 1 commit
Commits
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
26 changes: 24 additions & 2 deletions gguf-py/gguf/vocab.py
Original file line number Diff line number Diff line change
Expand Up @@ -122,8 +122,30 @@ def _try_load_from_tokenizer_json(self, path: Path) -> bool:
tokenizer = json.load(f)
if self.load_merges:
merges = tokenizer.get('model', {}).get('merges')
if isinstance(merges, list) and merges and isinstance(merges[0], str):
self.merges = merges
if isinstance(merges, list) and merges:
if isinstance(merges[0], str):
self.merges = merges
elif isinstance(merges[0], list) and len(merges[0]) == 2 and isinstance(merges[0][0], str):
# New format since transformers 4.45 to support spaces in merges
# ref: https://github.com/ggerganov/llama.cpp/issues/9692
# TODO: internally store as the new format instead of converting to old
if any(' ' in s for pair in merges for s in pair):
logger.warning(f'Spaces in merges detected, encoding as {chr(ord(" ") + 256)!r}')
self.merges = [
' '.join(
[
# ensure the spaces are properly encoded
''.join(
chr(ord(c) + 256) if c == ' ' else c
for c in part
)
for part in pair
]
)
for pair in merges
]
else:
raise ValueError("Unknown tokenizer merges format")
added_tokens = tokenizer.get('added_tokens', {})
else:
added_tokens = {}
Expand Down
Loading