vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 09:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	README.md
#	examples/server/README.md
#	examples/speculative/speculative.cpp
#	flake.lock
#	ggml/src/CMakeLists.txt
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-11-14 21:40:52 +08:00
commit df080b074d
41 changed files with 132106 additions and 130341 deletions
Download patch file Download diff file Expand all files Collapse all files

15
examples/server/server.cpp
View file

@ -656,11 +656,16 @@ struct server_context {
}
bool validate_model_chat_template() const {
llama_chat_message chat[] = {{"user", "test"}};
const int res = llama_chat_apply_template(model, nullptr, chat, 1, true, nullptr, 0);
return res > 0;
std::vector<char> model_template(2048, 0); // longest known template is about 1200 bytes
std::string template_key = "tokenizer.chat_template";
int32_t res = llama_model_meta_val_str(model, template_key.c_str(), model_template.data(), model_template.size());
if (res >= 0) {
llama_chat_message chat[] = {{"user", "test"}};
std::string tmpl = std::string(model_template.data(), model_template.size());
int32_t chat_res = llama_chat_apply_template(model, tmpl.c_str(), chat, 1, true, nullptr, 0);
return chat_res > 0;
}
return false;
}
void init() {