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
+2 -1
View File
@@ -272,7 +272,8 @@ class Keys:
CHAT_TEMPLATE_N = "tokenizer.chat_template.{name}"
CHAT_TEMPLATES = "tokenizer.chat_templates"
# Normalizer constants
NORMALIZER_LOWERCASE = "tokenizer.ggml.normalizer.lowercase"
NORMALIZER_LOWERCASE = "tokenizer.ggml.normalizer.lowercase"
NORMALIZER_STRIP_ACCENTS = "tokenizer.ggml.normalizer.strip_accents"
# FIM/Infill special tokens constants
FIM_PRE_ID = "tokenizer.ggml.fim_pre_token_id"
FIM_SUF_ID = "tokenizer.ggml.fim_suf_token_id"