llama.cpp
unicode : add opt-in NFC normalization for Unigram tokenizers
#30390
Merged

unicode : add opt-in NFC normalization for Unigram tokenizers #30390

sandrohanea
sandrohanea unicode : add opt-in NFC normalization for Unigram tokenizers
2e326a2f
sandrohanea sandrohanea requested a review from ggerganov ggerganov 17 days ago
sandrohanea sandrohanea requested a review from CISC CISC 17 days ago
github-actions github-actions added testing
github-actions github-actions added conversion
ggml-gh-bot
sandrohanea
sandrohanea
CISC
ggml-gh-bot
CISC
sandrohanea Fixing initial bot comments + linter error (using existing out instea…
1fa23096
sandrohanea
CISC
CISC commented on 2026-10-12
sandrohanea removed test_nfc_tokenizer
c8ff8f20
CISC
CISC approved these changes on 2026-10-12
CISC CISC added merge ready
ggerganov ggerganov merged 10da8c46 into master 15 days ago
ggerganov
sandrohanea sandrohanea deleted the sandroh/unigram-nfc branch 13 days ago
sandrohanea
sandrohanea
sandrohanea
sandrohanea
ggerganov
ckastner
ckastner
ggerganov
CISC

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone