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

convert : add BPE pre-tokenization for DBRX (#7132)

Browse source 
* Add BPE pre-tokenization for DBRX.

* Add vocab GGUFs.

* Remove test.

* Remove GGUFs.
This commit is contained in:
DAN™ 2024-05-08 06:43:23 -04:00 • committed by GitHub
parent 7e0b6a7b3b
commit 4cd621c26d
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

@ -4394,6 +4394,9 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "olmo") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_OLMO;
} else if (
tokenizer_pre == "dbrx") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DBRX;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@ -12200,6 +12203,7 @@ struct llm_tokenizer_bpe {
case LLAMA_VOCAB_TYPE_BPE:
switch (vocab.type_pre) {
case LLAMA_VOCAB_PRE_TYPE_LLAMA3:
case LLAMA_VOCAB_PRE_TYPE_DBRX:
word_collection = unicode_regex_split(text, {
// original regex from tokenizer.json
//"(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\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+",