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

Make string buffer dynamic

Browse source
This commit is contained in:
Bjarke Viksøe 2024-07-06 19:36:52 +02:00
parent 5475fc92d7
commit a21b89fd0e
1 changed files with 6 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
examples/server/server.cpp
View file

@ -2967,11 +2967,14 @@ int main(int argc, char ** argv) {
};
const auto handle_props = [&ctx_server](const httplib::Request & req, httplib::Response & res) {
std::vector<char> model_template(2048, 0); // longest known template is about 1200 bytes
std::string template_key = "tokenizer.chat_template", curr_tmpl;
int32_t tlen = llama_model_meta_val_str(ctx_server.model, template_key.c_str(), nullptr, 0);
if (tlen > 0) {
std::vector<char> model_template(tlen + 1, 0);
if (llama_model_meta_val_str(ctx_server.model, template_key.c_str(), model_template.data(), model_template.size()) > 0) {
curr_tmpl = std::string(model_template.data(), model_template.size());
}
}
res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
json data = {
{ "system_prompt", ctx_server.system_prompt.c_str() },