Hugging Face's logo

Spaces:
kazutab
/
mindmap-studio
Running on Zero

App Files Community
mindmap-studio
File size: 6,841 Bytes
0475af5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
#include "models.h"

void llama_model_gemma2::load_arch_hparams(llama_model_loader & ml) {
    hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
    hparams.n_swa = 4096; // default value of gemma 2
    uint32_t swa_period = 2;
    ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, swa_period, false);
    hparams.set_swa_pattern(swa_period);
    hparams.attn_soft_cap = true;
    hparams.rope_freq_base_train_swa  = hparams.rope_freq_base_train;
    hparams.rope_freq_scale_train_swa = hparams.rope_freq_scale_train;

    ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA,          hparams.rope_freq_base_train_swa, false);
    ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW,    hparams.n_swa, false);
    ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
    ml.get_key(LLM_KV_ATTN_LOGIT_SOFTCAPPING,      hparams.f_attn_logit_softcapping, false);
    ml.get_key(LLM_KV_FINAL_LOGIT_SOFTCAPPING,     hparams.f_final_logit_softcapping, false);

    switch (hparams.n_layer()) {
        case 26: type = LLM_TYPE_2B; break;
        case 42: type = LLM_TYPE_9B; break;
        case 46: type = LLM_TYPE_27B; break;
        default: type = LLM_TYPE_UNKNOWN;
   }

    // ref: https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py#L173
    hparams.f_attention_scale = type == LLM_TYPE_27B
        ? 1.0f / std::sqrt(float(hparams.n_embd / hparams.n_head(0)))
        : 1.0f / std::sqrt(float(hparams.n_embd_head_k()));
}

void llama_model_gemma2::load_arch_tensors(llama_model_loader &) {
    LLAMA_LOAD_LOCALS;

    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      = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD,  "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); // same as tok_embd, duplicated to allow offloading

    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);

        create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head, n_embd_k_gqa, n_embd_v_gqa, 0);
        layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd}, 0);
        layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", i), {n_embd}, 0);

        layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
        layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff}, 0);
        layer.ffn_up   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff}, 0);
        layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd}, 0);
        layer.ffn_post_norm = create_tensor(tn(LLM_TENSOR_FFN_POST_NORM, "weight", i), {n_embd}, 0);
    }
}

std::unique_ptr<llm_graph_context> llama_model_gemma2::build_arch_graph(const llm_graph_params & params) const {
    return std::make_unique<graph>(*this, params);
}

llama_model_gemma2::graph::graph(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
    const int64_t n_embd_head = hparams.n_embd_head_k();

    ggml_tensor * cur;
    ggml_tensor * inpL;

    inpL = build_inp_embd(model.tok_embd);

    inpL = ggml_scale(ctx0, inpL, sqrtf(n_embd));
    cb(inpL, "inp_scaled", -1);

    // inp_pos - contains the positions
    ggml_tensor * inp_pos = build_inp_pos();

    auto * inp_attn = build_attn_inp_kv_iswa();

    ggml_tensor * inp_out_ids = build_inp_out_ids();

    for (int il = 0; il < n_layer; ++il) {
        const float freq_base_l  = model.get_rope_freq_base (cparams, il);
        const float freq_scale_l = model.get_rope_freq_scale(cparams, il);

        // norm
        cur = build_norm(inpL,
                model.layers[il].attn_norm, NULL,
                LLM_NORM_RMS, il);
        cb(cur, "attn_norm", il);

        // self-attention
        {
            // compute Q and K and RoPE them
            auto [Qcur, Kcur, Vcur] = build_qkv(model.layers[il], cur,
                    n_embd_head, n_head, n_head_kv, il);

            Qcur = ggml_rope_ext(
                    ctx0, Qcur, inp_pos, nullptr,
                    n_rot, rope_type, n_ctx_orig, freq_base_l, freq_scale_l,
                    ext_factor, attn_factor, beta_fast, beta_slow);

            Kcur = ggml_rope_ext(
                    ctx0, Kcur, inp_pos, nullptr,
                    n_rot, rope_type, n_ctx_orig, freq_base_l, freq_scale_l,
                    ext_factor, attn_factor, beta_fast, beta_slow);

            cb(Qcur, "Qcur", il);
            cb(Kcur, "Kcur", il);
            cb(Vcur, "Vcur", il);

            Qcur = ggml_scale(ctx0, Qcur, hparams.f_attention_scale);

            cur = build_attn(inp_attn,
                    model.layers[il].wo, NULL, model.layers[il].wo_s,
                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f, il);
        }
        if (il == n_layer - 1 && inp_out_ids) {
            cur  = ggml_get_rows(ctx0,  cur, inp_out_ids);
            inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
        }
        cur = build_norm(cur,
                model.layers[il].attn_post_norm, NULL,
                LLM_NORM_RMS, il);
        cb(cur, "attn_post_norm", il);

        ggml_tensor * sa_out = ggml_add(ctx0, cur, inpL);
        cb(sa_out, "sa_out", il);

        cur = build_norm(sa_out,
                model.layers[il].ffn_norm, NULL,
                LLM_NORM_RMS, il);
        cb(cur, "ffn_norm", il);

        // feed-forward network
        {
            cur = build_ffn(cur,
                    model.layers[il].ffn_up,   NULL, NULL,
                    model.layers[il].ffn_gate, NULL, NULL,
                    model.layers[il].ffn_down, NULL, NULL,
                    NULL,
                    LLM_FFN_GELU, LLM_FFN_PAR, il);
            cb(cur, "ffn_out", il);
        }
        cur = build_norm(cur,
                model.layers[il].ffn_post_norm, NULL,
                LLM_NORM_RMS, -1);
        cb(cur, "ffn_post_norm", -1);

        cur = ggml_add(ctx0, cur, sa_out);

        cur = build_cvec(cur, il);
        cb(cur, "l_out", il);

        // input for next layer
        inpL = cur;
    }
    cur = inpL;

    cur = build_norm(cur,
            model.output_norm, NULL,
            LLM_NORM_RMS, -1);

    cb(cur, "result_norm", -1);
    res->t_embd = cur;

    // lm_head
    cur = build_lora_mm(model.output, cur, model.output_s);

    // final logit soft-capping
    cur = ggml_scale(ctx0, cur, 1.0f / hparams.f_final_logit_softcapping);
    cur = ggml_tanh(ctx0, cur);
    cur = ggml_scale(ctx0, cur, hparams.f_final_logit_softcapping);

    cb(cur, "result_output", -1);
    res->t_logits = cur;

    ggml_build_forward_expand(gf, cur);
}