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

server : add llama2 chat template (#5425)

Browse source 
* server: add mistral chat template

* server: fix typo

* server: rename template mistral to llama2

* server: format_llama2: remove BOS

* server: validate "--chat-template" argument

* server: clean up using_chatml variable

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
This commit is contained in:
Xuan Son Nguyen 2024-02-11 11:16:22 +01:00 • committed by GitHub
parent f026f8120f
commit 907e08c110
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 56 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

22
examples/server/server.cpp
View file

@ -36,6 +36,7 @@ struct server_params
std::string hostname = "127.0.0.1";
std::vector<std::string> api_keys;
std::string public_path = "examples/server/public";
std::string chat_template = "chatml";
int32_t port = 8080;
int32_t read_timeout = 600;
int32_t write_timeout = 600;
@ -1859,6 +1860,8 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
printf(" types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
printf(" -gan N, --grp-attn-n N set the group attention factor to extend context size through self-extend(default: 1=disabled), used together with group attention width `--grp-attn-w`");
printf(" -gaw N, --grp-attn-w N set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n`");
printf(" --chat-template FORMAT_NAME");
printf(" set chat template, possible valus is: llama2, chatml (default %s)", sparams.chat_template.c_str());
printf("\n");
}
@ -2290,6 +2293,21 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
log_set_target(stdout);
LOG_INFO("logging to file is disabled.", {});
}
else if (arg == "--chat-template")
{
if (++i >= argc)
{
invalid_param = true;
break;
}
std::string value(argv[i]);
if (value != "chatml" && value != "llama2") {
fprintf(stderr, "error: chat template can be \"llama2\" or \"chatml\", but got: %s\n", value.c_str());
invalid_param = true;
break;
}
sparams.chat_template = value;
}
else if (arg == "--override-kv")
{
if (++i >= argc) {
@ -2743,13 +2761,13 @@ int main(int argc, char **argv)
// TODO: add mount point without "/v1" prefix -- how?
svr.Post("/v1/chat/completions", [&llama, &validate_api_key](const httplib::Request &req, httplib::Response &res)
svr.Post("/v1/chat/completions", [&llama, &validate_api_key, &sparams](const httplib::Request &req, httplib::Response &res)
{
res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
if (!validate_api_key(req, res)) {
return;
}
json data = oaicompat_completion_params_parse(json::parse(req.body));
json data = oaicompat_completion_params_parse(json::parse(req.body), sparams.chat_template);
const int task_id = llama.queue_tasks.get_new_id();
llama.queue_results.add_waiting_task_id(task_id);