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

bring back missing --alias

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-09-05 20:58:10 +02:00
parent fe6df473a3
commit b1657cb934
1 changed files with 10 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

14
common/common.cpp
View file

@ -650,7 +650,6 @@ std::vector<llama_arg> gpt_params_parser_init(gpt_params & params, llama_example
sampler_type_names += llama_sampling_type_to_str(sampler_type) + ";"; sampler_type_names += llama_sampling_type_to_str(sampler_type) + ";";
} }
sampler_type_names.pop_back(); sampler_type_names.pop_back();
const char split_delim = ',';
/** /**
@ -1804,6 +1803,13 @@ std::vector<llama_arg> gpt_params_parser_init(gpt_params & params, llama_example
params.control_vector_layer_end = std::stoi(end); params.control_vector_layer_end = std::stoi(end);
} }
)); ));
add_opt(llama_arg(
{"-a", "--alias"}, "STRING",
"set alias for model name (to be used by REST API)",
[&params](std::string value) {
params.model_alias = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MODEL"));
add_opt(llama_arg( add_opt(llama_arg(
{"-m", "--model"}, "FNAME", {"-m", "--model"}, "FNAME",
ex == LLAMA_EXAMPLE_EXPORT_LORA ex == LLAMA_EXAMPLE_EXPORT_LORA
@ -1950,7 +1956,7 @@ std::vector<llama_arg> gpt_params_parser_init(gpt_params & params, llama_example
{"-npp"}, "n0,n1,...", {"-npp"}, "n0,n1,...",
"number of prompt tokens", "number of prompt tokens",
[&params](std::string value) { [&params](std::string value) {
auto p = string_split<int>(value, split_delim); auto p = string_split<int>(value, ',');
params.n_pp.insert(params.n_pp.end(), p.begin(), p.end()); params.n_pp.insert(params.n_pp.end(), p.begin(), p.end());
} }
).set_examples({LLAMA_EXAMPLE_BENCH})); ).set_examples({LLAMA_EXAMPLE_BENCH}));
@ -1958,7 +1964,7 @@ std::vector<llama_arg> gpt_params_parser_init(gpt_params & params, llama_example
{"-ntg"}, "n0,n1,...", {"-ntg"}, "n0,n1,...",
"number of text generation tokens", "number of text generation tokens",
[&params](std::string value) { [&params](std::string value) {
auto p = string_split<int>(value, split_delim); auto p = string_split<int>(value, ',');
params.n_tg.insert(params.n_tg.end(), p.begin(), p.end()); params.n_tg.insert(params.n_tg.end(), p.begin(), p.end());
} }
).set_examples({LLAMA_EXAMPLE_BENCH})); ).set_examples({LLAMA_EXAMPLE_BENCH}));
@ -1966,7 +1972,7 @@ std::vector<llama_arg> gpt_params_parser_init(gpt_params & params, llama_example
{"-npl"}, "n0,n1,...", {"-npl"}, "n0,n1,...",
"number of parallel prompts", "number of parallel prompts",
[&params](std::string value) { [&params](std::string value) {
auto p = string_split<int>(value, split_delim); auto p = string_split<int>(value, ',');
params.n_pl.insert(params.n_pl.end(), p.begin(), p.end()); params.n_pl.insert(params.n_pl.end(), p.begin(), p.end());
} }
).set_examples({LLAMA_EXAMPLE_BENCH})); ).set_examples({LLAMA_EXAMPLE_BENCH}));