Method build_baichuan

llama.cpp:5206–5324

    }

    struct ggml_cgraph * build_baichuan() {
        struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, LLAMA_MAX_NODES, false);

        struct ggml_tensor * cur;
        struct ggml_tensor * inpL;

        inpL = llm_build_inp_embd(ctx0, hparams, batch, model.tok_embd, cb);
        cb(inpL, "inp_embd", -1);

        // inp_pos - contains the positions
        struct ggml_tensor * inp_pos = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens);
        cb(inp_pos, "inp_pos", -1);

        // KQ_scale
        struct ggml_tensor * KQ_scale = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, 1);
        cb(KQ_scale, "KQ_scale", -1);

        // KQ_mask (mask for 1 head, it will be broadcasted to all heads)
        struct ggml_tensor * KQ_mask = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_kv, n_tokens, 1);
        cb(KQ_mask, "KQ_mask", -1);

        // shift the entire K-cache if needed
        if (do_rope_shift) {
            llm_build_k_shift(ctx0, hparams, cparams, kv_self, gf, LLM_ROPE, n_ctx, n_embd_head, freq_base, freq_scale, cb);
        }

        for (int il = 0; il < n_layer; ++il) {
            struct ggml_tensor * inpSA = inpL;

            cur = llm_build_norm(ctx0, inpL, hparams,
                    model.layers[il].attn_norm, NULL,
                    LLM_NORM_RMS, cb, il);
            cb(cur, "attn_norm", il);

            // self-attention
            {
                struct ggml_tensor * Qcur = ggml_mul_mat(ctx0, model.layers[il].wq, cur);
                cb(Qcur, "Qcur", il);

                struct ggml_tensor * Kcur = ggml_mul_mat(ctx0, model.layers[il].wk, cur);
                cb(Kcur, "Kcur", il);

                struct ggml_tensor * Vcur = ggml_mul_mat(ctx0, model.layers[il].wv, cur);
                cb(Vcur, "Vcur", il);

                switch (model.type) {
                    case MODEL_7B:
                        Qcur = ggml_rope_custom(
                            ctx0, ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens), inp_pos,
                            n_embd_head, 0, 0, n_orig_ctx, freq_base, freq_scale,
                            ext_factor, attn_factor, beta_fast, beta_slow
                        );
                        Kcur = ggml_rope_custom(
                            ctx0, ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens), inp_pos,
                            n_embd_head, 0, 0, n_orig_ctx, freq_base, freq_scale,
                            ext_factor, attn_factor, beta_fast, beta_slow
                        );
                        break;