llama.cpp/src/models/phimoe.cpp

#include "models.h"

void llama_model_phimoe::load_arch_hparams(llama_model_loader & ml) {
    ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);

    switch (hparams.n_layer()) {
        case 32: type = LLM_TYPE_16x3_8B; break;
        default: type = LLM_TYPE_UNKNOWN;
    }
}

void llama_model_phimoe::load_arch_tensors(llama_model_loader &) {
    LLAMA_LOAD_LOCALS;

    const int64_t n_embd_head = n_embd / n_head;

    tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0);

    // output
    output_norm   = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0);
    output_norm_b = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd}, 0);
    output        = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), { n_embd, n_vocab }, 0);
    output_b      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "bias"),   { n_vocab }, 0);

    for (int i = 0; i < n_layer; ++i) {
        auto & layer = layers[i];

        layer.attn_norm   = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), { n_embd }, 0);
        layer.attn_norm_b = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "bias",   i), { n_embd }, 0);

        create_tensor_qkv(layer, i, n_embd, n_embd, n_embd_gqa, n_embd_gqa, 0);
        layer.wo   = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), { n_embd, n_embd }, 0);
        layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias",   i), { n_embd }, 0);

        layer.ffn_norm   = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), { n_embd }, 0);
        layer.ffn_norm_b = create_tensor(tn(LLM_TENSOR_FFN_NORM, "bias",   i), { n_embd }, 0);

        layer.ffn_gate_inp  = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP,  "weight", i), {n_embd, n_expert},         0);
        layer.ffn_gate_exps = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff,   n_expert}, 0);
        layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff,   n_embd, n_expert}, 0);
        layer.ffn_up_exps   = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS,   "weight", i), {n_embd, n_ff,   n_expert}, 0);

        layer.rope_long  = create_tensor(tn(LLM_TENSOR_ROPE_FACTORS_LONG,  "weight", i), { n_embd_head/2 }, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 0));
        layer.rope_short = create_tensor(tn(LLM_TENSOR_ROPE_FACTORS_SHORT, "weight", i), { n_embd_head/2 }, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 0));
     }
}

std::unique_ptr<llm_graph_context> llama_model_phimoe::build_arch_graph(const llm_graph_params & params) const {
    if (hparams.swa_type != LLAMA_SWA_TYPE_NONE) {
        return std::make_unique<graph<true>> (*this, params);
    } else {
        return std::make_unique<graph<false>>(*this, params);
    }
}