Method load_model

examples/server/server.cpp:539–577

    }

    bool load_model(const gpt_params &params_)
    {
        params = params_;
        if (!params.mmproj.empty()) {
            multimodal = true;
            LOG_TEE("Multi Modal Mode Enabled");
            clp_ctx = clip_model_load(params.mmproj.c_str(), /*verbosity=*/ 1);
            if(clp_ctx == nullptr) {
                LOG_ERROR("unable to load clip model", {{"model", params.mmproj}});
                return false;
            }

            if (params.n_ctx < 2048) { // request larger context for the image embedding
                params.n_ctx = 2048;
            }
        }

        std::tie(model, ctx) = llama_init_from_gpt_params(params);
        if (model == nullptr)
        {
            LOG_ERROR("unable to load model", {{"model", params.model}});
            return false;
        }

        if (multimodal) {
            const int n_embd_clip = clip_n_mmproj_embd(clp_ctx);
            const int n_embd_llm  = llama_n_embd(model);
            if (n_embd_clip != n_embd_llm) {
                LOG_TEE("%s: embedding dim of the multimodal projector (%d) is not equal to that of LLaMA (%d). Make sure that you use the correct mmproj file.\n", __func__, n_embd_clip, n_embd_llm);
                llama_free(ctx);
                llama_free_model(model);
                return false;
            }
        }

        n_ctx = llama_n_ctx(ctx);

        return true;
    }

    void initialize() {
        id_gen = 0;