Skip to content

fix: converter hf now handles byte characters. Closes #188 #189

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
Mar 22, 2025
Merged

fix: converter hf now handles byte characters. Closes #188 #189

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
7 changes: 6 additions & 1 deletion converter/convert-tokenizer-hf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,12 @@ def resolveLlamaTokenizer(self):
t = processor.id_to_piece(i)
s = processor.get_score(i)
t = t.replace('▁', ' ') # sentencepiece uses this character as whitespace
b = t.encode('utf-8')
# Check for byte characters
if len(t) == 6 and t.startswith('<0x') and t.endswith('>'):
# For example, "<0x0A>"" is a newline character
b = bytearray.fromhex(t[3:-1])
else:
b = t.encode('utf-8')
self.tokens.append(b)
self.scores.append(s)

Expand Down