vocab : refactor normalizer flags into options struct, add strip_accents (#24371)

* vocab : refactor normalizer flags into options struct, add strip_accents

* Update src/llama-vocab.h

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-vocab.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
o7si
2026-06-11 10:36:50 +03:00
committed by GitHub
co-authored by Sigbjørn Skjæret
parent db94854ff5
commit 68f30663cf
7 changed files with 84 additions and 51 deletions
+3
View File
@@ -1124,6 +1124,9 @@ class GGUFWriter:
def add_normalizer_lowercase(self, value: bool) -> None:
self.add_bool(Keys.Tokenizer.NORMALIZER_LOWERCASE, value)
def add_normalizer_strip_accents(self, value: bool) -> None:
self.add_bool(Keys.Tokenizer.NORMALIZER_STRIP_ACCENTS, value)
def add_eot_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.EOT_ID, id)