Class Gemma3_Text_Only

src/include/AutoModel/modeling_gemma3_text.hpp:26–40

Gemma3_Text_Only **************/

/************              Gemma3_Text_Only            **************/
class Gemma3_Text_Only : public AutoModel {
private:

    void setup_tokenizer(std::string model_path);

public:
    Gemma3_Text_Only(xrt::device* npu_device_inst);

    void load_model(std::string model_path, json model_inf, int default_context_length = -1, bool enable_preemption = false) override;
    //void toggle_enable_think() override;
    bool insert(chat_meta_info_t& meta_info, lm_uniform_input_t& input, std::function<bool()> is_cancelled = [] { return false; }) override;
    std::string generate(chat_meta_info_t& meta_info, int length_limit, std::ostream& os, std::function<bool()> is_cancelled = [] { return false; }) override;
    std::string generate_with_prompt(chat_meta_info_t& meta_info, lm_uniform_input_t& input, int length_limit, std::ostream& os = std::cout) override;
    std::string apply_chat_template(nlohmann::ordered_json& messages, nlohmann::ordered_json tools = nlohmann::ordered_json::object()) override;
};