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

llama : add Smaug 70B support (#7402)

Browse source
This commit is contained in:
Bartowski 2024-05-26 08:28:35 -04:00 • committed by GitHub
parent 9146d36fe7
commit c429b33beb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 9 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -4593,6 +4593,9 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "dbrx") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DBRX;
} else if (
tokenizer_pre == "smaug-bpe") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_SMAUG;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@ -12512,6 +12515,7 @@ struct llm_tokenizer_bpe {
});
break;
case LLAMA_VOCAB_PRE_TYPE_DBRX:
case LLAMA_VOCAB_PRE_TYPE_SMAUG:
word_collection = unicode_regex_split(text, {
// 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+",