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

Wire LLM_KV_TOKENIZER_CHAT_TEMPLATE_N in llama_model_chat_template

Browse source
This commit is contained in:
ochafik 2025-01-13 19:58:15 +00:00
parent cb72cf1fc3
commit 78861a3eb2
7 changed files with 17 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/run/run.cpp
View file

@ -713,11 +713,11 @@ static void add_message(const char * role, const std::string & text, LlamaData &
// Function to apply the chat template and resize `formatted` if needed
static int apply_chat_template(LlamaData & llama_data, const bool append) {
int result = llama_chat_apply_template(
llama_model_chat_template(llama_data.model.get()), llama_data.messages.data(), llama_data.messages.size(), append,
llama_model_chat_template(llama_data.model.get(), /* name */ nullptr), llama_data.messages.data(), llama_data.messages.size(), append,
append ? llama_data.fmtted.data() : nullptr, append ? llama_data.fmtted.size() : 0);
if (append && result > static_cast<int>(llama_data.fmtted.size())) {
llama_data.fmtted.resize(result);
result = llama_chat_apply_template(llama_model_chat_template(llama_data.model.get()), llama_data.messages.data(),
result = llama_chat_apply_template(llama_model_chat_template(llama_data.model.get(), /* name */ nullptr), llama_data.messages.data(),
llama_data.messages.size(), append, llama_data.fmtted.data(),
llama_data.fmtted.size());
}