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

Add German Umlauts to Default COMPLETE_ALPHABET #151

Open
johannesscheibe opened this issue Dec 4, 2024 · 0 comments
Open

Add German Umlauts to Default COMPLETE_ALPHABET #151

johannesscheibe opened this issue Dec 4, 2024 · 0 comments

Comments

@johannesscheibe
Copy link

Current Behavior

The current alphabet validation does not support German umlauts (ä, ö, ü) by default.

COMPLETE_ALPHABET = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!@#$%^&*()_+-=[]{};:,./<>? `'\""

This is currently configurable via the CharacterLevelParserConfig but leads to the issue that third party frameworks need to add the support as well (e.g. vllm).

Expected Behavior

The alphabet validation should recognize and accept the following German characters by default:

  • ä, Ä
  • ö, Ö
  • ü, Ü
  • ß (sharp s/eszett)

Environment

  • lm-format-enforcer version: 0.10.9
  • Python version: 3.12.2
  • OS: MacOs Sequoia 15.1.1

Related

  • vllm integration
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant