llama-cpp-sys-4 0.4.3

Low Level Bindings to llama.cpp
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84

#include "models.h"

ggml_tensor * clip_graph_minimax_m3::apply_rope(
        ggml_tensor * x, ggml_tensor * pos_h, ggml_tensor * pos_w) {
    const int64_t Hn  = x->ne[1];
    const int64_t P   = x->ne[2];
    const size_t  es  = ggml_element_size(x);
    const int     dh  = (int) x->ne[0];
    const int     axd = 2 * ((2 * (dh / 2) / 3) / 2);

    GGML_ASSERT(x->nb[0] == es);
    GGML_ASSERT(3 * axd <= dh);

    const float th  = hparams.rope_theta;

    // layout of x is [t, h, w, pad]
    // t is unrotated, h and w are rotated, pad is unrotated
    // note: everything from n_dims onward untouched, so w and pad are rotated in one call.
    auto sl = [&](int off, int n) {
        return ggml_cont(ctx0, ggml_view_3d(ctx0, x, n, Hn, P, x->nb[1], x->nb[2], (size_t) off * es));
    };
    ggml_tensor * t = sl(0,       axd);
    ggml_tensor * h = sl(axd,     axd);
    ggml_tensor * w = sl(2 * axd, dh - 2 * axd); // w + pad

    h = ggml_rope_ext(ctx0, h, pos_h, nullptr, axd, GGML_ROPE_TYPE_NEOX, 0, th, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f);
    w = ggml_rope_ext(ctx0, w, pos_w, nullptr, axd, GGML_ROPE_TYPE_NEOX, 0, th, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f);
    return ggml_concat(ctx0, ggml_concat(ctx0, t, h, 0), w, 0);
}

ggml_cgraph * clip_graph_minimax_m3::build() {
    GGML_ASSERT(model.patch_bias     == nullptr);
    GGML_ASSERT(model.class_embedding == nullptr);
    GGML_ASSERT(model.patch_embeddings_0 && model.patch_embeddings_1);
    GGML_ASSERT(model.mm_1_w && model.mm_2_w);
    GGML_ASSERT(model.mm_merger_fc1_w && model.mm_merger_fc2_w);

    const int batch_size = 1;
    const int n_pos      = n_patches;
    const int merge      = hparams.n_merge;

    // patch embedding
    ggml_tensor * inp_raw = build_inp_raw();
    ggml_tensor * inp = ggml_add(ctx0,
        ggml_conv_2d(ctx0, model.patch_embeddings_0, inp_raw, patch_size, patch_size, 0, 0, 1, 1),
        ggml_conv_2d(ctx0, model.patch_embeddings_1, inp_raw, patch_size, patch_size, 0, 0, 1, 1));

    // spatial merge
    {
        inp = ggml_permute(ctx0, inp, 1, 2, 0, 3);
        inp = ggml_cont_4d(ctx0, inp, n_embd * merge, n_patches_x / merge, n_patches_y, batch_size);
        inp = ggml_reshape_4d(ctx0, inp, n_embd * merge, n_patches_x / merge, merge, batch_size * (n_patches_y / merge));
        inp = ggml_permute(ctx0, inp, 0, 2, 1, 3);
        inp = ggml_cont_3d(ctx0, inp, n_embd, n_patches_x * n_patches_y, batch_size);
    }

    // t (time axis) is always 0 for now, so we leave it unrotated
    ggml_tensor * pos_h = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_pos);
    ggml_set_name(pos_h, "minimax_pos_h"); ggml_set_input(pos_h);
    ggml_tensor * pos_w = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_pos);
    ggml_set_name(pos_w, "minimax_pos_w"); ggml_set_input(pos_w);

    ggml_tensor * inpL = build_vit(
        inp, n_pos, NORM_TYPE_NORMAL, FFN_GELU_ERF, nullptr,
        [&](ggml_tensor * c, const clip_layer &) {
            return apply_rope(c, pos_h, pos_w);
        });

    // projector
    ggml_tensor * emb = inpL;
    emb = build_ffn(emb, model.mm_1_w, model.mm_1_b,
                    nullptr, nullptr,
                    model.mm_2_w, model.mm_2_b, FFN_GELU_ERF, -1);

    const int64_t proj = emb->ne[0];
    emb = ggml_reshape_2d(ctx0, emb, proj * merge * merge, n_pos / (merge * merge));

    emb = build_ffn(emb, model.mm_merger_fc1_w, model.mm_merger_fc1_b,
                    nullptr, nullptr,
                    model.mm_merger_fc2_w, model.mm_merger_fc2_b, FFN_GELU_ERF, -1);

    ggml_build_forward_expand(gf, emb);
    return gf;
}