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

llama : add support for Tekken pre-tokenizer (#8579)

Browse source 
* llama : Added support for Tekken pre-tokenizer (#8577)

Removed uneeded `vocab.tokenizer_clean_spaces` assignment

* llama : fix order of pre-tokenizers

* * Tekken pre-tokenizer no longer uses clean_up_tokenization_spaces
* Updated chkhsh for Tekken tokenizer

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Michael Coppola 2024-07-20 09:43:51 -04:00 • committed by GitHub
parent 69b9945b44
commit 940362224d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 18 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

13
src/llama.cpp
View file

@ -5524,6 +5524,12 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "jais") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_JAIS;
} else if (
tokenizer_pre == "tekken") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_TEKKEN;
vocab.tokenizer_clean_spaces = false;
vocab.tokenizer_ignore_merges = true;
vocab.tokenizer_add_bos = true;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
@ -15585,6 +15591,13 @@ struct llm_tokenizer_bpe {
"\\p{N}",
};
break;
case LLAMA_VOCAB_PRE_TYPE_TEKKEN:
// original regex from tokenizer.json
// "[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]*[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]+|[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]+[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]*|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
regex_exprs = {
"[^\\r\\n\\p{L}\\p{N}]?((?=[\\p{L}])([^a-z]))*((?=[\\p{L}])([^A-Z]))+|[^\\r\\n\\p{L}\\p{N}]?((?=[\\p{L}])([^a-z]))+((?=[\\p{L}])([^A-Z]))*|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
};
break;
default:
// default regex for BPE tokenization pre-processing
regex_exprs = {