common: support remote preset (#18520)
* arg: support remote preset * proof reading * allow one HF repo to point to multiple HF repos * docs: mention about multiple GGUF use case * correct clean_file_name * download: also return HTTP status code * fix case with cache file used * fix --offline option
This commit is contained in:
Xuan-Son Nguyen
+116
-51
@@ -6,6 +6,7 @@
|
||||
#include "log.h"
|
||||
#include "sampling.h"
|
||||
#include "download.h"
|
||||
#include "preset.h"
|
||||
|
||||
// fix problem with std::min and std::max
|
||||
#if defined(_WIN32)
|
||||
@@ -268,6 +269,46 @@ static void parse_tensor_buffer_overrides(const std::string & value, std::vector
|
||||
}
|
||||
}
|
||||
|
||||
static std::string clean_file_name(const std::string & fname) {
|
||||
std::string clean_fname = fname;
|
||||
string_replace_all(clean_fname, "\\", "_");
|
||||
string_replace_all(clean_fname, "/", "_");
|
||||
return clean_fname;
|
||||
}
|
||||
|
||||
static bool common_params_handle_remote_preset(common_params & params, llama_example ex) {
|
||||
GGML_ASSERT(!params.model.hf_repo.empty());
|
||||
|
||||
const bool offline = params.offline;
|
||||
std::string model_endpoint = get_model_endpoint();
|
||||
auto preset_url = model_endpoint + params.model.hf_repo + "/resolve/main/preset.ini";
|
||||
|
||||
// prepare local path for caching
|
||||
auto preset_fname = clean_file_name(params.model.hf_repo + "_preset.ini");
|
||||
auto preset_path = fs_get_cache_file(preset_fname);
|
||||
const int status = common_download_file_single(preset_url, preset_path, params.hf_token, offline);
|
||||
const bool has_preset = status >= 200 && status < 400;
|
||||
|
||||
// remote preset is optional, so we don't error out if not found
|
||||
if (has_preset) {
|
||||
LOG_INF("applying remote preset from %s\n", preset_url.c_str());
|
||||
common_preset_context ctx(ex, /* only_remote_allowed */ true);
|
||||
common_preset global; // unused for now
|
||||
auto remote_presets = ctx.load_from_ini(preset_path, global);
|
||||
if (remote_presets.find(COMMON_PRESET_DEFAULT_NAME) != remote_presets.end()) {
|
||||
common_preset & preset = remote_presets.at(COMMON_PRESET_DEFAULT_NAME);
|
||||
LOG_INF("\n%s", preset.to_ini().c_str()); // to_ini already added trailing newline
|
||||
preset.apply_to_params(params);
|
||||
} else {
|
||||
throw std::runtime_error("Remote preset.ini does not contain [" + std::string(COMMON_PRESET_DEFAULT_NAME) + "] section");
|
||||
}
|
||||
} else {
|
||||
LOG_INF("%s", "no remote preset found, skipping\n");
|
||||
}
|
||||
|
||||
return has_preset;
|
||||
}
|
||||
|
||||
struct handle_model_result {
|
||||
bool found_mmproj = false;
|
||||
common_params_model mmproj;
|
||||
@@ -309,9 +350,7 @@ static handle_model_result common_params_handle_model(
|
||||
// make sure model path is present (for caching purposes)
|
||||
if (model.path.empty()) {
|
||||
// this is to avoid different repo having same file name, or same file name in different subdirs
|
||||
std::string filename = model.hf_repo + "_" + model.hf_file;
|
||||
// to make sure we don't have any slashes in the filename
|
||||
string_replace_all(filename, "/", "_");
|
||||
std::string filename = clean_file_name(model.hf_repo + "_" + model.hf_file);
|
||||
model.path = fs_get_cache_file(filename);
|
||||
}
|
||||
|
||||
@@ -425,61 +464,87 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
|
||||
}
|
||||
};
|
||||
|
||||
std::set<std::string> seen_args;
|
||||
auto parse_cli_args = [&]() {
|
||||
std::set<std::string> seen_args;
|
||||
|
||||
for (int i = 1; i < argc; i++) {
|
||||
const std::string arg_prefix = "--";
|
||||
for (int i = 1; i < argc; i++) {
|
||||
const std::string arg_prefix = "--";
|
||||
|
||||
std::string arg = argv[i];
|
||||
if (arg.compare(0, arg_prefix.size(), arg_prefix) == 0) {
|
||||
std::replace(arg.begin(), arg.end(), '_', '-');
|
||||
}
|
||||
if (arg_to_options.find(arg) == arg_to_options.end()) {
|
||||
throw std::invalid_argument(string_format("error: invalid argument: %s", arg.c_str()));
|
||||
}
|
||||
if (!seen_args.insert(arg).second) {
|
||||
LOG_WRN("DEPRECATED: argument '%s' specified multiple times, use comma-separated values instead (only last value will be used)\n", arg.c_str());
|
||||
}
|
||||
auto & tmp = arg_to_options[arg];
|
||||
auto opt = *tmp.first;
|
||||
bool is_positive = tmp.second;
|
||||
if (opt.has_value_from_env()) {
|
||||
fprintf(stderr, "warn: %s environment variable is set, but will be overwritten by command line argument %s\n", opt.env, arg.c_str());
|
||||
}
|
||||
try {
|
||||
if (opt.handler_void) {
|
||||
opt.handler_void(params);
|
||||
continue;
|
||||
std::string arg = argv[i];
|
||||
if (arg.compare(0, arg_prefix.size(), arg_prefix) == 0) {
|
||||
std::replace(arg.begin(), arg.end(), '_', '-');
|
||||
}
|
||||
if (opt.handler_bool) {
|
||||
opt.handler_bool(params, is_positive);
|
||||
continue;
|
||||
if (arg_to_options.find(arg) == arg_to_options.end()) {
|
||||
throw std::invalid_argument(string_format("error: invalid argument: %s", arg.c_str()));
|
||||
}
|
||||
if (!seen_args.insert(arg).second) {
|
||||
LOG_WRN("DEPRECATED: argument '%s' specified multiple times, use comma-separated values instead (only last value will be used)\n", arg.c_str());
|
||||
}
|
||||
auto & tmp = arg_to_options[arg];
|
||||
auto opt = *tmp.first;
|
||||
bool is_positive = tmp.second;
|
||||
if (opt.has_value_from_env()) {
|
||||
fprintf(stderr, "warn: %s environment variable is set, but will be overwritten by command line argument %s\n", opt.env, arg.c_str());
|
||||
}
|
||||
try {
|
||||
if (opt.handler_void) {
|
||||
opt.handler_void(params);
|
||||
continue;
|
||||
}
|
||||
if (opt.handler_bool) {
|
||||
opt.handler_bool(params, is_positive);
|
||||
continue;
|
||||
}
|
||||
|
||||
// arg with single value
|
||||
check_arg(i);
|
||||
std::string val = argv[++i];
|
||||
if (opt.handler_int) {
|
||||
opt.handler_int(params, std::stoi(val));
|
||||
continue;
|
||||
}
|
||||
if (opt.handler_string) {
|
||||
opt.handler_string(params, val);
|
||||
continue;
|
||||
}
|
||||
// arg with single value
|
||||
check_arg(i);
|
||||
std::string val = argv[++i];
|
||||
if (opt.handler_int) {
|
||||
opt.handler_int(params, std::stoi(val));
|
||||
continue;
|
||||
}
|
||||
if (opt.handler_string) {
|
||||
opt.handler_string(params, val);
|
||||
continue;
|
||||
}
|
||||
|
||||
// arg with 2 values
|
||||
check_arg(i);
|
||||
std::string val2 = argv[++i];
|
||||
if (opt.handler_str_str) {
|
||||
opt.handler_str_str(params, val, val2);
|
||||
continue;
|
||||
// arg with 2 values
|
||||
check_arg(i);
|
||||
std::string val2 = argv[++i];
|
||||
if (opt.handler_str_str) {
|
||||
opt.handler_str_str(params, val, val2);
|
||||
continue;
|
||||
}
|
||||
} catch (std::exception & e) {
|
||||
throw std::invalid_argument(string_format(
|
||||
"error while handling argument \"%s\": %s\n\n"
|
||||
"usage:\n%s\n\nto show complete usage, run with -h",
|
||||
arg.c_str(), e.what(), opt.to_string().c_str()));
|
||||
}
|
||||
} catch (std::exception & e) {
|
||||
throw std::invalid_argument(string_format(
|
||||
"error while handling argument \"%s\": %s\n\n"
|
||||
"usage:\n%s\n\nto show complete usage, run with -h",
|
||||
arg.c_str(), e.what(), opt.to_string().c_str()));
|
||||
}
|
||||
};
|
||||
|
||||
// parse the first time to get -hf option (used for remote preset)
|
||||
parse_cli_args();
|
||||
|
||||
// maybe handle remote preset
|
||||
if (!params.model.hf_repo.empty()) {
|
||||
std::string cli_hf_repo = params.model.hf_repo;
|
||||
bool has_preset = common_params_handle_remote_preset(params, ctx_arg.ex);
|
||||
|
||||
// special case: if hf_repo explicitly set by preset, we need to preserve it (ignore CLI value)
|
||||
// this is useful when we have one HF repo pointing to other HF repos (one model - multiple GGUFs)
|
||||
std::string preset_hf_repo = params.model.hf_repo;
|
||||
bool preset_has_hf_repo = preset_hf_repo != cli_hf_repo;
|
||||
|
||||
if (has_preset) {
|
||||
// re-parse CLI args to override preset values
|
||||
parse_cli_args();
|
||||
}
|
||||
|
||||
// preserve hf_repo from preset if needed
|
||||
if (preset_has_hf_repo) {
|
||||
params.model.hf_repo = preset_hf_repo;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user