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

Add chat template support for llama-cli (#8068)

Browse source 
* add chat template support for llama-cli

* add help message

* server: simplify format_chat

* more consistent naming

* improve

* add llama_chat_format_example

* fix server

* code style

* code style

* Update examples/main/main.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Xuan Son Nguyen 2024-06-25 13:56:49 +02:00 • committed by GitHub
parent 3791ad2193
commit 48e6b92cc3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 154 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

29
examples/server/utils.hpp
View file

@ -118,36 +118,17 @@ static inline void server_log(const char * level, const char * function, int lin
// Format given chat. If tmpl is empty, we take the template from model metadata
inline std::string format_chat(const struct llama_model * model, const std::string & tmpl, const std::vector<json> & messages) {
size_t alloc_size = 0;
// vector holding all allocated string to be passed to llama_chat_apply_template
std::vector<std::string> str(messages.size() * 2);
std::vector<llama_chat_message> chat(messages.size());
std::vector<llama_chat_msg> chat;
for (size_t i = 0; i < messages.size(); ++i) {
const auto & curr_msg = messages[i];
str[i*2 + 0] = json_value(curr_msg, "role", std::string(""));
str[i*2 + 1] = json_value(curr_msg, "content", std::string(""));
alloc_size += str[i*2 + 1].length();
chat[i].role = str[i*2 + 0].c_str();
chat[i].content = str[i*2 + 1].c_str();
std::string role = json_value(curr_msg, "role", std::string(""));
std::string content = json_value(curr_msg, "content", std::string(""));
chat.push_back({role, content});
}
const char * ptr_tmpl = tmpl.empty() ? nullptr : tmpl.c_str();
std::vector<char> buf(alloc_size * 2);
// run the first time to get the total output length
int32_t res = llama_chat_apply_template(model, ptr_tmpl, chat.data(), chat.size(), true, buf.data(), buf.size());
// if it turns out that our buffer is too small, we resize it
if ((size_t) res > buf.size()) {
buf.resize(res);
res = llama_chat_apply_template(model, ptr_tmpl, chat.data(), chat.size(), true, buf.data(), buf.size());
}
const std::string formatted_chat(buf.data(), res);
auto formatted_chat = llama_chat_apply_template(model, tmpl, chat, true);
LOG_VERBOSE("formatted_chat", {{"text", formatted_chat.c_str()}});
return formatted_chat;
}