vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 10:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

model : add Kimi-K2 support (#14654)

Browse source 
* Kimi-K2 conversion

* add Kimi_K2  pre type

* Kimi-K2

* Kimi-K2 unicode

* Kimi-K2

* LLAMA_MAX_EXPERTS 384

* fix vocab iteration

* regex space fix

* add kimi-k2 to pre_computed_hashes

* Updated with kimi-k2 get_vocab_base_pre hash

* fix whitespaces

* fix flake errors

* remove more unicode.cpp whitespaces

* change set_vocab() flow

* add moonshotai-Kimi-K2.jinja to /models/templates/

* update moonshotai-Kimi-K2.jinja

* add kimi-k2 chat template

* add kimi-k2

* update NotImplementedError

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* except Exception

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* LLM_CHAT_TEMPLATE_KIMI_K2 if(add_ass){}

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Gabriel Larson 2025-07-15 14:54:22 -05:00 • committed by GitHub
parent ba1ceb3456
commit 4a4f426944
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 345 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/llama-vocab.cpp
View file

@ -405,6 +405,13 @@ struct llm_tokenizer_bpe : llm_tokenizer {
"[^\\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;
case LLAMA_VOCAB_PRE_TYPE_KIMI_K2:
regex_exprs = {
// K2 trigger pattern - this will activate the custom K2 handler in unicode.cpp
// The custom handler implements all K2 patterns with proper Han character exclusion
"\\p{Han}+",
};
break;
case LLAMA_VOCAB_PRE_TYPE_SUPERBPE:
regex_exprs = {
"\\p{N}+",
@ -1954,6 +1961,10 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
tokenizer_pre == "hunyuan") {
pre_type = LLAMA_VOCAB_PRE_TYPE_HUNYUAN;
clean_spaces = false;
} else if (
tokenizer_pre == "kimi-k2") {
pre_type = LLAMA_VOCAB_PRE_TYPE_KIMI_K2;
clean_spaces = false;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}