mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-28 09:55:41 +01:00
cb8f4fa3f8
* Set C locale for consistent float formatting across all binaries. * Add C locale setting to all tools binaries Add std::setlocale(LC_NUMERIC, "C") to all 16 binaries in the tools/ directory to ensure consistent floating-point formatting. * Apply suggestion from @JohannesGaessler --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
44 lines
1.1 KiB
C++
44 lines
1.1 KiB
C++
#include "arg.h"
|
|
#include "common.h"
|
|
#include "ngram-cache.h"
|
|
#include "llama.h"
|
|
|
|
#include <clocale>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
int main(int argc, char ** argv){
|
|
std::setlocale(LC_NUMERIC, "C");
|
|
|
|
common_params params;
|
|
|
|
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_LOOKUP)) {
|
|
return 1;
|
|
}
|
|
|
|
// init llama.cpp
|
|
llama_backend_init();
|
|
llama_numa_init(params.numa);
|
|
|
|
// load the model
|
|
auto llama_init = common_init_from_params(params);
|
|
|
|
auto * model = llama_init->model();
|
|
auto * ctx = llama_init->context();
|
|
|
|
GGML_ASSERT(model != nullptr);
|
|
|
|
// tokenize the prompt
|
|
std::vector<llama_token> inp;
|
|
inp = common_tokenize(ctx, params.prompt, true, true);
|
|
fprintf(stderr, "%s: tokenization done\n", __func__);
|
|
|
|
common_ngram_cache ngram_cache;
|
|
common_ngram_cache_update(ngram_cache, LLAMA_NGRAM_STATIC, LLAMA_NGRAM_STATIC, inp, inp.size(), true);
|
|
fprintf(stderr, "%s: hashing done, writing file to %s\n", __func__, params.speculative.lookup_cache_static.c_str());
|
|
|
|
common_ngram_cache_save(ngram_cache, params.speculative.lookup_cache_static);
|
|
|
|
return 0;
|
|
}
|