| #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; |
|
|
| common_init(); |
|
|
| if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_LOOKUP)) { |
| return 1; |
| } |
|
|
| |
| llama_backend_init(); |
| llama_numa_init(params.numa); |
|
|
| |
| auto llama_init = common_init_from_params(params); |
|
|
| auto * model = llama_init->model(); |
| auto * ctx = llama_init->context(); |
|
|
| GGML_ASSERT(model != nullptr); |
|
|
| |
| 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.ngram_cache.lookup_cache_static.c_str()); |
|
|
| common_ngram_cache_save(ngram_cache, params.speculative.ngram_cache.lookup_cache_static); |
|
|
| return 0; |
| } |
|
|
