Method load_hparams

subprojects/llama.cpp/src/llama-model.cpp:490–2465

}

void llama_model::load_hparams(llama_model_loader & ml) {
    const gguf_context * ctx = ml.meta.get();

    // get metadata as string
    for (int i = 0; i < gguf_get_n_kv(ctx); i++) {
        gguf_type type = gguf_get_kv_type(ctx, i);
        if (type == GGUF_TYPE_ARRAY) {
            continue;
        }
        const char * name = gguf_get_key(ctx, i);
        const std::string value = gguf_kv_to_str(ctx, i);
        gguf_kv.emplace(name, value);
    }

    // get general kv
    ml.get_key(LLM_KV_GENERAL_NAME, name, false);

    // everything past this point is not vocab-related
    // for CLIP models, we only need to load tensors, no hparams
    if (hparams.vocab_only || ml.get_arch() == LLM_ARCH_CLIP) {
        return;
    }

    ml.get_key(LLM_KV_CONTEXT_LENGTH,          hparams.n_ctx_train);
    ml.get_key(LLM_KV_EMBEDDING_LENGTH,        hparams.n_embd);
    ml.get_key(LLM_KV_EMBEDDING_LENGTH_OUT,    hparams.n_embd_out_impl, false);
    ml.get_key(LLM_KV_BLOCK_COUNT,             hparams.n_layer);
    ml.get_key(LLM_KV_EXPERT_COUNT,            hparams.n_expert,        false);
    ml.get_key(LLM_KV_EXPERT_USED_COUNT,       hparams.n_expert_used,   false);
    ml.get_key(LLM_KV_EXPERT_GROUP_COUNT,      hparams.n_expert_groups, false);
    ml.get_key(LLM_KV_EXPERT_GROUP_USED_COUNT, hparams.n_group_used,    false);

    if (arch == LLM_ARCH_WAVTOKENIZER_DEC) {
        ml.get_key(LLM_KV_FEATURES_LENGTH, hparams.n_embd_features);

        ml.get_key(LLM_KV_POSNET_EMBEDDING_LENGTH, hparams.posnet.n_embd);
        ml.get_key(LLM_KV_POSNET_BLOCK_COUNT,      hparams.posnet.n_layer);

        ml.get_key(LLM_KV_CONVNEXT_EMBEDDING_LENGTH, hparams.convnext.n_embd);
        ml.get_key(LLM_KV_CONVNEXT_BLOCK_COUNT,      hparams.convnext.n_layer);
    }

    GGML_ASSERT(hparams.n_expert <= LLAMA_MAX_EXPERTS);
    GGML_ASSERT(hparams.n_expert_used <= hparams.n_expert);
    if (hparams.n_expert > 0) {
        GGML_ASSERT(hparams.n_expert_used > 0);
        GGML_ASSERT(hparams.n_expert_groups < hparams.n_expert);
        if (hparams.n_expert_groups > 1) {
            GGML_ASSERT(hparams.n_expert % hparams.n_expert_groups == 0);
            GGML_ASSERT(hparams.n_group_used > 0);
            GGML_ASSERT(hparams.n_group_used < hparams.n_expert_groups);
        }
    } else {
        GGML_ASSERT(hparams.n_expert_used == 0);
        GGML_ASSERT(hparams.n_expert_groups == 0);
    }

    std::fill(hparams.n_head_arr.begin(),    hparams.n_head_arr.end(),    0);