Skip to content

Fallback to tokenizer.json if vocab.json does not exist #6245

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

Closed
wants to merge 1 commit into from
Closed

Fallback to tokenizer.json if vocab.json does not exist #6245

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
13 changes: 7 additions & 6 deletions convert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1293,19 +1293,20 @@ def load_some_model(path: Path) -> ModelPlus:


class VocabFactory:
_FILES = {"spm": "tokenizer.model", "bpe": "vocab.json", "hfft": "tokenizer.json"}
_FILES = {"spm": ["tokenizer.model"], "bpe": ["vocab.json", "tokenizer.json"], "hfft": ["tokenizer.json"]}

def __init__(self, path: Path):
self.path = path
self.file_paths = self._detect_files()
print(f"Found vocab files: {self.file_paths}")

def _detect_files(self) -> dict[str, Path | None]:
def locate(file: str) -> Path | None:
if (path := self.path / file).exists():
return path
if (path := self.path.parent / file).exists():
return path
def locate(files: list[str]) -> Path | None:
for file in files:
if (path := self.path / file).exists():
return path
if (path := self.path.parent / file).exists():
return path
return None

return {vt: locate(f) for vt, f in self._FILES.items()}
Expand Down