tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases 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
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)
//