aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-11-09 15:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

examples : add --alias option to gpt_params to set use friendly model name (#1614)

Browse source
This commit is contained in:
Vladimir Zorin 2023-05-28 20:14:24 +03:00 committed by GitHub
parent bb051d9723
commit 337aea1139
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 21 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
examples/common.cpp
View file

@ -251,6 +251,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
break;
}
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") {
if (++i >= argc) {
invalid_param = true;

1
examples/common.h
View file

@ -45,6 +45,7 @@ struct gpt_params {
float mirostat_eta = 0.10f; // learning rate
std::string model = "models/7B/ggml-model.bin"; // model path
std::string model_alias = "unknown"; // model alias
std::string prompt = "";
std::string path_prompt_cache = ""; // path to file for saving/loading prompt eval state
std::string input_prefix = ""; // string to prefix user inputs with

16
examples/server/server.cpp
View file

@ -400,8 +400,10 @@ void server_print_usage(int /*argc*/, char **argv, const gpt_params &params)
fprintf(stderr, " number of layers to store in VRAM\n");
fprintf(stderr, " -m FNAME, --model FNAME\n");
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, " -port PORT port to listen (default 8080)\n");
fprintf(stderr, " -a ALIAS, --alias ALIAS\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");
}
@ -453,6 +455,15 @@ bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_para
}
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")
{
params.embedding = true;
@ -645,6 +656,7 @@ int main(int argc, char **argv)
try
{
json data = {
{"model", llama.params.model_alias },
{"content", llama.generated_text },
{"tokens_predicted", llama.num_tokens_predicted}};
return res.set_content(data.dump(), "application/json");