Fix merge: 'smaug'

This commit is contained in:
jaime-m-p 2024-06-12 23:01:10 +02:00
parent c863752ca7
commit 75840fe6a6

View file

@ -12963,6 +12963,7 @@ struct llm_tokenizer_bpe {
};
break;
case LLAMA_VOCAB_PRE_TYPE_DBRX:
case LLAMA_VOCAB_PRE_TYPE_SMAUG:
regex_exprs = {
// same as llama3
"(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",