Function export_lora

examples/export-lora/export-lora.cpp:371–462

}

static void export_lora(struct export_lora_params * params) {
    // load all loras
    std::vector<struct lora_data *> loras;
    for (size_t i = 0; i < params->lora.size(); ++i) {
        struct lora_data * lora = load_lora(&params->lora[i]);
        if (lora != NULL) {
            loras.push_back(lora);
        }
    }
    if (loras.size() == 0) {
        fprintf(stderr, "warning: no lora adapters will be applied.\n");
    }

    // open input file
    struct llama_file fin(params->fn_model_base.c_str(), "rb");
    if (!fin.fp) {
        die_fmt("Could not open file '%s'\n", params->fn_model_base.c_str());
    }

    // open base model gguf, read tensors without their data
    struct ggml_context * ctx_in;
    struct gguf_init_params params_gguf;
    params_gguf.no_alloc = true;
    params_gguf.ctx      = &ctx_in;
    struct gguf_context * gguf_in = gguf_init_from_file(params->fn_model_base.c_str(), params_gguf);

    // create new gguf
    struct gguf_context * gguf_out = gguf_init_empty();

    // copy meta data from base model: kv and tensors
    gguf_set_kv(gguf_out, gguf_in);
    int n_tensors = gguf_get_n_tensors(gguf_in);
    for (int i=0; i < n_tensors; ++i) {
        const char * name = gguf_get_tensor_name(gguf_in, i);
        struct ggml_tensor * tensor = ggml_get_tensor(ctx_in, name);
        gguf_add_tensor(gguf_out, tensor);
    }

    // create output file
    struct llama_file fout(params->fn_model_out.c_str(), "wb");
    if (!fout.fp) {
        die_fmt("Could not create file '%s'\n", params->fn_model_out.c_str());
    }

    // write gguf meta data
    std::vector<uint8_t> meta;
    meta.resize(gguf_get_meta_size(gguf_out));
    gguf_get_meta_data(gguf_out, meta.data());
    fout.write_raw(meta.data(), meta.size());

    std::vector<uint8_t> data;
    std::vector<uint8_t> padding;
    for (int i=0; i < n_tensors; ++i) {
        const char * name = gguf_get_tensor_name(gguf_in, i);
        struct ggml_tensor * tensor = ggml_get_tensor(ctx_in, name);

        // read tensor data
        data.resize(ggml_nbytes(tensor));