Function load_opt_context_gguf

common/train.cpp:537–594

}

void load_opt_context_gguf(struct gguf_context * fctx, struct ggml_context * f_ggml_ctx, struct ggml_opt_context * opt) {
    // NOTE: gguf_context must be initialized with f_ggml_ctx and no_alloc=false, otherwise tensor data can not be read

    uint32_t file_version;
    GGUF_GET_KEY(fctx, file_version, gguf_get_val_u32, GGUF_TYPE_UINT32, true, LLM_KV_OPTIMIZER_FILE_VERSION);
    GGML_ASSERT(file_version == 0);

    GGUF_GET_KEY(fctx, opt->params.past, gguf_get_val_u32, GGUF_TYPE_UINT32, true, LLM_KV_OPTIMIZER_CONVERGENCE_PAST_COUNT);
    GGUF_GET_KEY(fctx, opt->iter, gguf_get_val_u32, GGUF_TYPE_UINT32, true, LLM_KV_OPTIMIZER_ITERATION_COUNT);
    GGUF_GET_KEY(fctx, opt->just_initialized, gguf_get_val_bool, GGUF_TYPE_BOOL, true, LLM_KV_OPTIMIZER_JUST_INITIALIZED);

    uint64_t nx;
    GGUF_GET_KEY(fctx, nx, gguf_get_val_u64, GGUF_TYPE_UINT64, true, LLM_KV_OPTIMIZER_PARAMETER_COUNT);
    opt->nx = (size_t) nx;

    // don't call ggml_opt_init until optimizer type and optimizer specific parameters are know

    std::string opt_type;
    GGUF_GET_KEY(fctx, opt_type, gguf_get_val_str, GGUF_TYPE_STRING, true, LLM_KV_OPTIMIZER_TYPE);
    if (opt_type == LLM_KV_OPTIMIZER_TYPE_ADAM) {
        opt->params.type = GGML_OPT_ADAM;

        GGUF_GET_KEY(fctx, opt->adam.fx_best,          gguf_get_val_f32, GGUF_TYPE_FLOAT32, true, LLM_KV_OPTIMIZER_ADAM_BEST_LOSS);
        GGUF_GET_KEY(fctx, opt->adam.fx_prev,          gguf_get_val_f32, GGUF_TYPE_FLOAT32, true, LLM_KV_OPTIMIZER_ADAM_PREVIOUS_LOSS);
        GGUF_GET_KEY(fctx, opt->adam.n_no_improvement, gguf_get_val_u32, GGUF_TYPE_UINT32,  true, LLM_KV_OPTIMIZER_ADAM_NO_IMPROVEMENT_COUNT);

        ggml_opt_init(opt->ctx, opt, opt->params, opt->nx);

        copy_tensor_by_name(opt->adam.m,  f_ggml_ctx, LLM_TENSOR_OPTIMIZER_ADAM_FIRST_MOMENTS);
        copy_tensor_by_name(opt->adam.v,  f_ggml_ctx, LLM_TENSOR_OPTIMIZER_ADAM_SECOND_MOMENTS);
        copy_tensor_by_name(opt->adam.pf, f_ggml_ctx, LLM_TENSOR_OPTIMIZER_ADAM_PAST_LOSS_VALUES);
    } else if (opt_type == LLM_KV_OPTIMIZER_TYPE_LBFGS) {
        opt->params.type = GGML_OPT_LBFGS;

        GGUF_GET_KEY(fctx, opt->params.lbfgs.m,         gguf_get_val_u32, GGUF_TYPE_UINT32,  true, LLM_KV_OPTIMIZER_LBFGS_APPROX_HESSIAN_COUNT);
        GGUF_GET_KEY(fctx, opt->lbfgs.fx_best,          gguf_get_val_f32, GGUF_TYPE_FLOAT32, true, LLM_KV_OPTIMIZER_LBFGS_BEST_LOSS);
        GGUF_GET_KEY(fctx, opt->lbfgs.step,             gguf_get_val_f32, GGUF_TYPE_FLOAT32, true, LLM_KV_OPTIMIZER_LBFGS_LINE_SEARCH_STEP);
        GGUF_GET_KEY(fctx, opt->lbfgs.j,                gguf_get_val_i32, GGUF_TYPE_INT32,   true, LLM_KV_OPTIMIZER_LBFGS_LINE_SEARCH_J);
        GGUF_GET_KEY(fctx, opt->lbfgs.k,                gguf_get_val_i32, GGUF_TYPE_INT32,   true, LLM_KV_OPTIMIZER_LBFGS_LINE_SEARCH_K);
        GGUF_GET_KEY(fctx, opt->lbfgs.end,              gguf_get_val_i32, GGUF_TYPE_INT32,   true, LLM_KV_OPTIMIZER_LBFGS_LINE_SEARCH_END);
        GGUF_GET_KEY(fctx, opt->lbfgs.n_no_improvement, gguf_get_val_u32, GGUF_TYPE_UINT32,  true, LLM_KV_OPTIMIZER_LBFGS_NO_IMPROVEMENT_COUNT);

        ggml_opt_init(opt->ctx, opt, opt->params, opt->nx);

        copy_tensor_by_name(opt->lbfgs.x,    f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_CURRENT_PARAMETERS);
        copy_tensor_by_name(opt->lbfgs.xp,   f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_PREVIOUS_PARAMETERS);
        copy_tensor_by_name(opt->lbfgs.g,    f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_CURRENT_GRADIENTS);
        copy_tensor_by_name(opt->lbfgs.gp,   f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_PREVIOUS_GRADIENTS);
        copy_tensor_by_name(opt->lbfgs.d,    f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_SEARCH_DIRECTION);
        copy_tensor_by_name(opt->lbfgs.pf,   f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_PAST_LOSS_VALUES);
        copy_tensor_by_name(opt->lbfgs.lmal, f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_MEMORY_ALPHA);
        copy_tensor_by_name(opt->lbfgs.lmys, f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_MEMORY_YS);
        copy_tensor_by_name(opt->lbfgs.lms,  f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_MEMORY_S);
        copy_tensor_by_name(opt->lbfgs.lmy,  f_ggml_ctx, LLM_TENSOR_OPTIMIZER_LBFGS_MEMORY_Y);
    } else {
        die("unknown optimizer type\n");
    }
}