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

implment olmo pre-tokenizer type in llama.cpp

Browse source
This commit is contained in:
nopperl 2024-05-07 20:51:54 +02:00
parent 69432502cd
commit 25be8f5cd5
2 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -4389,6 +4389,9 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "command-r") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_COMMAND_R;
} else if (
tokenizer_pre == "olmo") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_OLMO;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@ -12248,6 +12251,7 @@ struct llm_tokenizer_bpe {
});
break;
case LLAMA_VOCAB_PRE_TYPE_GPT2:
case LLAMA_VOCAB_PRE_TYPE_OLMO:
word_collection = unicode_regex_split(text, {
"'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
});

1
llama.h
View file

@ -81,6 +81,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_GPT2 = 7,
LLAMA_VOCAB_PRE_TYPE_REFACT = 8,
LLAMA_VOCAB_PRE_TYPE_COMMAND_R = 9,
LLAMA_VOCAB_PRE_TYPE_OLMO = 10,
};
// note: these values should be synchronized with ggml_rope