Method cmd_load

src/runner/runner.cpp:408–441

\brief Load a model \param input_list, std::vector

/// \brief Load a model
/// \param input_list, std::vector<std::string>
void Runner::cmd_load(std::vector<std::string>& input_list) {
    std::string model_name = input_list[1];

    std::pair<std::string, std::unique_ptr<AutoModel>> auto_model = get_auto_model(model_name, this->supported_models, &this->npu_device_inst);
    model_name = auto_model.first;

    if (model_name != this->tag) {
        this->tag = model_name;

        if (!this->downloader.is_model_downloaded(this->tag)) {
            this->downloader.pull_model(this->tag);
        }
        auto_chat_engine.reset();
        if(model_name=="gpt-oss:20b")
            std::this_thread::sleep_for(std::chrono::milliseconds(2800));
        this->auto_chat_engine = std::move(auto_model.second);

        auto [new_tag, model_info] = this->supported_models.get_model_info(this->tag);
        this->auto_chat_engine->configure_parameter("img_pre_resize", this->img_pre_resize);
        try {
            this->auto_chat_engine->load_model(this->supported_models.get_model_path(new_tag), model_info, this->ctx_length, this->preemption);
        }
        catch (const std::exception& e) {
            header_print("ERROR", "Failed to load model: " + std::string(e.what()));
            exit(EXIT_FAILURE);
        }

        this->auto_chat_engine->configure_parameter("system_prompt", this->system_prompt);

    }
    else
        header_print("FLM", "Model already loaded: " << model_name);

}

/// \brief Save the history
/// \param input_list, std::vector<std::string>