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

server : clean up built-in template detection (#11026)

Browse source 
* server : clean up built-in template detection

* fix compilation

* add chat template test

* fix condition
This commit is contained in:
Xuan Son Nguyen 2024-12-31 15:22:01 +01:00 • committed by GitHub
parent 5896c65232
commit 45095a61bf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 44 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

13
examples/server/utils.hpp
View file

@ -382,19 +382,6 @@ inline std::string format_chat(const struct llama_model * model, const std::stri
return formatted_chat;
}
static std::string llama_get_chat_template(const struct llama_model * model) {
std::string template_key = "tokenizer.chat_template";
// call with NULL buffer to get the total size of the string
int32_t res = llama_model_meta_val_str(model, template_key.c_str(), NULL, 0);
if (res < 2) {
return "";
} else {
std::vector<char> model_template(res + 1, 0);
llama_model_meta_val_str(model, template_key.c_str(), model_template.data(), model_template.size());
return std::string(model_template.data(), model_template.size() - 1);
}
}
//
// base64 utils (TODO: move to common in the future)
//