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

llama : add Phi-4-mini support (supersede #12099) (#12108)

Browse source 
* Added Phi-4-mini-instruct support

* Update regex per ngxson

* Change the vocab base to Xenova/gpt-4o

* fix conversion update script

* no need to check longrope

* minor style fix

* fix python style

---------

Co-authored-by: Nicholas Sparks <nisparks@microsoft.com>
This commit is contained in:
Xuan-Son Nguyen 2025-02-28 12:44:11 +01:00 • committed by GitHub
parent 84d5f4bc19
commit c43a3e7996
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 191 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/llama-vocab.cpp
View file

@ -392,6 +392,13 @@ struct llm_tokenizer_bpe : llm_tokenizer {
"'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
};
break;
case LLAMA_VOCAB_PRE_TYPE_GPT4O:
regex_exprs = {
// 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}]+(?i:'s|'t|'re|'ve|'m|'ll|'d)?|[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]+[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]*(?i:'s|'t|'re|'ve|'m|'ll|'d)?|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
"[^\\r\\n\\p{L}\\p{N}]?((?=[\\p{L}])([^a-z]))*((?=[\\p{L}])([^A-Z]))+(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])?|[^\\r\\n\\p{L}\\p{N}]?((?=[\\p{L}])([^a-z]))+((?=[\\p{L}])([^A-Z]))*(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])?|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
};
break;
default:
// default regex for BPE tokenization pre-processing
regex_exprs = {
@ -1592,6 +1599,10 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
} else if (
tokenizer_pre == "megrez") {
pre_type = LLAMA_VOCAB_PRE_TYPE_QWEN2;
} else if (
tokenizer_pre == "gpt-4o") {
pre_type = LLAMA_VOCAB_PRE_TYPE_GPT4O;
clean_spaces = false;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}