ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

vocab : BailingMoE : change possessive quantifiers to greedy (#12677)

Browse source
This commit is contained in:
Sigbjørn Skjæret 2025-04-02 11:21:48 +02:00 • committed by GitHub
parent 42eb248f46
commit 83a88bd6af
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
src/llama-vocab.cpp
View file

@ -411,7 +411,8 @@ struct llm_tokenizer_bpe : llm_tokenizer {
regex_exprs = {
// original regex from tokenizer.json
// "'(?i:[sdmt]|ll|ve|re)|[^\\r\\n\\p{L}\\p{N}]?+\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]++[\\r\\n]*|\\s*[\\r\\n]|\\s+(?!\\S)|\\s+"
"'(?:[sSdDmMtT]|[lL][lL]|[vV][eE]|[rR][eE])|[^\\r\\n\\p{L}\\p{N}]?+\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]++[\\r\\n]*|\\s*[\\r\\n]|\\s+(?!\\S)|\\s+",
// FIXME? Changed possessive quantifiers (?+ and ++) to greedy to avoid errors and imatrix hanging (tried atomic grouping but it's not supported?)
"'(?:[sSdDmMtT]|[lL][lL]|[vV][eE]|[rR][eE])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]|\\s+(?!\\S)|\\s+",
};
break;
default: