Method load_hparams

smallthinker/src/llama-model.cpp:457–1512

}

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
    if (hparams.vocab_only) {
        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_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);

    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);
    } else {
        GGML_ASSERT(hparams.n_expert_used == 0);
    }

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

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

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

    ml.get_key_or_arr(LLM_KV_FEED_FORWARD_LENGTH,  hparams.n_ff_arr,   hparams.n_layer, false);
    ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT, hparams.n_head_arr, hparams.n_layer, false);

    // n_head_kv is optional, default to n_head