mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-24 10:24:35 +00:00
examples : add --alias option to gpt_params to set use friendly model name (#1614)
This commit is contained in:
parent
bb051d9723
commit
337aea1139
@ -251,6 +251,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
|
|||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
params.model = argv[i];
|
params.model = argv[i];
|
||||||
|
} else if (arg == "-a" || arg == "--alias") {
|
||||||
|
if (++i >= argc) {
|
||||||
|
invalid_param = true;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
params.model_alias = argv[i];
|
||||||
} else if (arg == "--lora") {
|
} else if (arg == "--lora") {
|
||||||
if (++i >= argc) {
|
if (++i >= argc) {
|
||||||
invalid_param = true;
|
invalid_param = true;
|
||||||
|
@ -45,6 +45,7 @@ struct gpt_params {
|
|||||||
float mirostat_eta = 0.10f; // learning rate
|
float mirostat_eta = 0.10f; // learning rate
|
||||||
|
|
||||||
std::string model = "models/7B/ggml-model.bin"; // model path
|
std::string model = "models/7B/ggml-model.bin"; // model path
|
||||||
|
std::string model_alias = "unknown"; // model alias
|
||||||
std::string prompt = "";
|
std::string prompt = "";
|
||||||
std::string path_prompt_cache = ""; // path to file for saving/loading prompt eval state
|
std::string path_prompt_cache = ""; // path to file for saving/loading prompt eval state
|
||||||
std::string input_prefix = ""; // string to prefix user inputs with
|
std::string input_prefix = ""; // string to prefix user inputs with
|
||||||
|
@ -400,8 +400,10 @@ void server_print_usage(int /*argc*/, char **argv, const gpt_params ¶ms)
|
|||||||
fprintf(stderr, " number of layers to store in VRAM\n");
|
fprintf(stderr, " number of layers to store in VRAM\n");
|
||||||
fprintf(stderr, " -m FNAME, --model FNAME\n");
|
fprintf(stderr, " -m FNAME, --model FNAME\n");
|
||||||
fprintf(stderr, " model path (default: %s)\n", params.model.c_str());
|
fprintf(stderr, " model path (default: %s)\n", params.model.c_str());
|
||||||
fprintf(stderr, " -host ip address to listen (default 127.0.0.1)\n");
|
fprintf(stderr, " -a ALIAS, --alias ALIAS\n");
|
||||||
fprintf(stderr, " -port PORT port to listen (default 8080)\n");
|
fprintf(stderr, " set an alias for the model, will be added as `model` field in completion response\n");
|
||||||
|
fprintf(stderr, " --host ip address to listen (default 127.0.0.1)\n");
|
||||||
|
fprintf(stderr, " --port PORT port to listen (default 8080)\n");
|
||||||
fprintf(stderr, "\n");
|
fprintf(stderr, "\n");
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -453,6 +455,15 @@ bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_para
|
|||||||
}
|
}
|
||||||
params.model = argv[i];
|
params.model = argv[i];
|
||||||
}
|
}
|
||||||
|
else if (arg == "-a" || arg == "--alias")
|
||||||
|
{
|
||||||
|
if (++i >= argc)
|
||||||
|
{
|
||||||
|
invalid_param = true;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
params.model_alias = argv[i];
|
||||||
|
}
|
||||||
else if (arg == "--embedding")
|
else if (arg == "--embedding")
|
||||||
{
|
{
|
||||||
params.embedding = true;
|
params.embedding = true;
|
||||||
@ -645,6 +656,7 @@ int main(int argc, char **argv)
|
|||||||
try
|
try
|
||||||
{
|
{
|
||||||
json data = {
|
json data = {
|
||||||
|
{"model", llama.params.model_alias },
|
||||||
{"content", llama.generated_text },
|
{"content", llama.generated_text },
|
||||||
{"tokens_predicted", llama.num_tokens_predicted}};
|
{"tokens_predicted", llama.num_tokens_predicted}};
|
||||||
return res.set_content(data.dump(), "application/json");
|
return res.set_content(data.dump(), "application/json");
|
||||||
|
Loading…
Reference in New Issue
Block a user