Method common_init_result

subprojects/llama.cpp/common/common.cpp:1092–1190

};

common_init_result::common_init_result(common_params & params) :
    pimpl(new impl{}) {
    auto mparams = common_model_params_to_llama(params);
    auto cparams = common_context_params_to_llama(params);

    if (params.fit_params) {
        LOG_INF("%s: fitting params to device memory, for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on\n", __func__);
        llama_params_fit(params.model.path.c_str(), &mparams, &cparams,
            params.tensor_split,
            params.tensor_buft_overrides.data(),
            params.fit_params_target.data(),
            params.fit_params_min_ctx,
            params.verbosity >= 4 ? GGML_LOG_LEVEL_DEBUG : GGML_LOG_LEVEL_ERROR);
    }

    llama_model * model = llama_model_load_from_file(params.model.path.c_str(), mparams);
    if (model == NULL) {
        return;
    }

    pimpl->model.reset(model);

    const llama_vocab * vocab = llama_model_get_vocab(model);

    // load and optionally apply lora adapters (must be loaded before context creation)
    for (auto & la : params.lora_adapters) {
        llama_adapter_lora_ptr lora;
        lora.reset(llama_adapter_lora_init(model, la.path.c_str()));
        if (lora == nullptr) {
            LOG_ERR("%s: failed to load lora adapter '%s'\n", __func__, la.path.c_str());
            pimpl->model.reset(model);
            return;
        }

        char buf[1024];
        la.ptr = lora.get();
        llama_adapter_meta_val_str(la.ptr, "adapter.lora.task_name", buf, sizeof(buf));
        la.task_name = buf;
        llama_adapter_meta_val_str(la.ptr, "adapter.lora.prompt_prefix", buf, sizeof(buf));
        la.prompt_prefix = buf;
        pimpl->lora.emplace_back(std::move(lora)); // copy to list of loaded adapters
    }

    // updates params.sampling
    // TODO: fix naming
    common_init_sampler_from_model(model, params.sampling);

    if (params.sampling.ignore_eos && llama_vocab_eos(vocab) == LLAMA_TOKEN_NULL) {
        LOG_WRN("%s: warning: vocab does not have an EOS token, ignoring --ignore-eos\n", __func__);
        params.sampling.ignore_eos = false;
    }

    // initialize once
    for (llama_token i = 0; i < llama_vocab_n_tokens(vocab); i++) {
        if (llama_vocab_is_eog(vocab, i)) {
            LOG_INF("%s: added %s logit bias = %f\n", __func__, common_token_to_piece(vocab, i).c_str(), -INFINITY);
            params.sampling.logit_bias_eog.push_back({i, -INFINITY});
        }