vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 02:49:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	README.md
#	examples/parallel/parallel.cpp
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-blas/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/gguf.cpp
#	scripts/sync-ggml.last
#	tests/test-gguf.cpp
This commit is contained in:
Concedo 2025-06-02 23:26:43 +08:00
commit b42b618897
8 changed files with 89 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

9
src/llama-vocab.cpp
View file

@ -2319,9 +2319,11 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
std::string model_name;
std::string tokenizer_pre;
std::string general_arch;
ml.get_key(LLM_KV_GENERAL_NAME, model_name, false);
ml.get_key(LLM_KV_TOKENIZER_PRE, tokenizer_pre, false);
ml.get_key(LLM_KV_GENERAL_ARCHITECTURE, general_arch, false);
// model name to lowercase
std::transform(model_name.begin(), model_name.end(), model_name.begin(),
@ -2330,8 +2332,11 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
}
);
// set attributes by model/tokenizer name
if (_contains_any(tokenizer_pre, {"jina-v2-de", "jina-v2-es", "jina-v2-code"})) {
// set attributes by model/tokenizer/architecture name
if (false
|| _contains_any(tokenizer_pre, {"jina-v2-de", "jina-v2-es", "jina-v2-code"})
|| _contains_any(general_arch, {"nomic-bert-moe"})
) {
_set_token_attr("<mask>", LLAMA_TOKEN_ATTR_LSTRIP, true);
} else if (_contains_any(model_name, {"phi-3", "phi3"})) {
for (auto id : cache_special_tokens) {