mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 03:44:35 +00:00
llama : fix Viking pre-tokenizer regex
The order was previously wrong, which caused errors in some tests.
This commit is contained in:
parent
f9d42c598b
commit
31a1b0eeaa
@ -15440,8 +15440,8 @@ struct llm_tokenizer_bpe {
|
|||||||
break;
|
break;
|
||||||
case LLAMA_VOCAB_PRE_TYPE_VIKING:
|
case LLAMA_VOCAB_PRE_TYPE_VIKING:
|
||||||
regex_exprs = {
|
regex_exprs = {
|
||||||
"\\p{N}",
|
|
||||||
" ?[^(\\s|.,!?…。,、।۔،)]+",
|
" ?[^(\\s|.,!?…。,、।۔،)]+",
|
||||||
|
"\\p{N}",
|
||||||
};
|
};
|
||||||
break;
|
break;
|
||||||
default:
|
default:
|
||||||
|
Loading…
Reference in New Issue
Block a user