Function main

subprojects/llama.cpp/tests/test-tokenizer-0.cpp:126–312

}

int main(int argc, char **argv) {
    if (argc < 2) {
        fprintf(stderr, "Usage: %s vocab-file [text-file]\n", argv[0]);
        return 1;
    }

    const std::string fname = argv[1];

    const std::string fname_inp = fname + ".inp";
    const std::string fname_out = fname + ".out";

    std::string fname_text;
    if (argc > 2) {
        fname_text = argv[2];
    }

    fprintf(stderr, "%s : reading vocab from: '%s'\n", __func__, fname.c_str());

    llama_model * model;
    llama_context * ctx;

    llama_backend_init();

    // load the vocab
    {
        auto mparams = llama_model_default_params();

        mparams.vocab_only = true;

        model = llama_model_load_from_file(fname.c_str(), mparams);

        if (model == NULL) {
            fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
            return 1;
        }

        auto cparams = llama_context_default_params();

        ctx = llama_init_from_model(model, cparams);

        if (ctx == NULL) {
            fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
            llama_model_free(model);
            return 1;
        }
    }

#ifdef _WIN32
    // We need this for unicode console support
    console::init(false, false);
    atexit([]() { console::cleanup(); });
#endif

    bool success = true;

    const auto k_tests = [&]() -> llama_tests {
        if (!fname_text.empty()) {
            return {};