ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

server : better security control for public deployments (#9776)

Browse source 
* server : more explicit endpoint access settings

* protect /props endpoint

* fix tests

* update server docs

* fix typo

* fix tests
This commit is contained in:
Xuan Son Nguyen 2024-10-08 13:27:04 +02:00 • committed by GitHub
parent fa42aa6d89
commit 458367a906
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 126 additions and 116 deletions
Download patch file Download diff file Expand all files Collapse all files

13
examples/server/utils.hpp
View file

@ -90,6 +90,19 @@ 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 < 0) {
return "";
} else {
std::vector<char> model_template(res, 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());
}
}
//
// base64 utils (TODO: move to common in the future)
//