mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-20 13:14:09 +00:00
1cb7e1bf39
* spec : add self speculative decoding and ngram-mod and refactor common : use common_ prefix for common library function llama : use LLAMA_TOKEN_NULL spec : add self speculative decoding (no draft model required) + refactor spec : add ngram-mod spec : various improvements ton ngram-map + docs spec : fix the check-rate logic of ngram-simple common : add common_speculative_is_compat() spec : simplify time measurement using common_time_meas refactor common_sampler_init refactor common_token_to_piece refactor and fix cur_p bug clean up * spec : remove check rate * spec: show warnings instead of abort --------- Co-authored-by: firecoperana <firecoperana> Co-authored-by: Sascha Rogmann <59577610+srogmann@users.noreply.github.com>
28 lines
763 B
C++
28 lines
763 B
C++
#include "llama.h"
|
|
#include "get-model.h"
|
|
|
|
#include <cstdlib>
|
|
|
|
int main(int argc, char *argv[] ) {
|
|
auto * model_path = get_model_or_exit(argc, argv);
|
|
auto * file = fopen(model_path, "r");
|
|
if (file == nullptr) {
|
|
fprintf(stderr, "no model at '%s' found\n", model_path);
|
|
return EXIT_FAILURE;
|
|
}
|
|
|
|
fprintf(stderr, "using '%s'\n", model_path);
|
|
fclose(file);
|
|
|
|
llama_backend_init();
|
|
auto params = llama_model_params{};
|
|
params.use_mmap = false;
|
|
params.progress_callback = [](float progress, void * ctx){
|
|
(void) ctx;
|
|
return progress > 0.50;
|
|
};
|
|
auto * model = llama_model_load_from_file(model_path, params);
|
|
llama_backend_free();
|
|
return model == nullptr ? EXIT_SUCCESS : EXIT_FAILURE;
|
|
}
|