Hugging Face's logo

AJKADZ
/
PHI_CODER

GGUF
conversational
Model card Files
xet
 Community
PHI_CODER
File size: 3,852 Bytes
9b19fd8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#include "llama-hparams.h"

#include "ggml.h"

void llama_hparams::set_swa_pattern(uint32_t n_pattern, bool dense_first) {
    if (dense_first) {
        for (uint32_t il = 0; il < n_layer; ++il) {
            swa_layers[il] = n_pattern == 0 || (il % n_pattern != 0);
        }
    } else {
        for (uint32_t il = 0; il < n_layer; ++il) {
            swa_layers[il] = n_pattern == 0 || (il % n_pattern < (n_pattern - 1));
        }
    }
}

bool llama_hparams::is_swa_any() const {
    for (uint32_t il = 0; il < n_layer; ++il) {
        if (swa_layers[il]) {
            return true;
        }
    }

    return false;
}

uint32_t llama_hparams::n_head(uint32_t il) const {
    if (il < n_layer) {
        return n_head_arr[il];
    }

    GGML_ABORT("fatal error");
}

uint32_t llama_hparams::n_head_kv(uint32_t il) const {
    if (il < n_layer) {
        return n_head_kv_arr[il];
    }

    GGML_ABORT("fatal error");
}

uint32_t llama_hparams::n_ff(uint32_t il) const {
    if (il < n_layer) {
        return n_ff_arr[il];
    }

    GGML_ABORT("fatal error");
}

uint32_t llama_hparams::n_gqa(uint32_t il) const {
    const uint32_t n_head    = this->n_head(il);
    const uint32_t n_head_kv = this->n_head_kv(il);

    if (n_head_kv == 0) {
        return 0;
    }

    return n_head/n_head_kv;
}

uint32_t llama_hparams::n_embd_k_gqa(uint32_t il) const {
    const uint32_t n_head_kv = this->n_head_kv(il);

    return n_embd_head_k * n_head_kv;
}

uint32_t llama_hparams::n_embd_v_gqa(uint32_t il) const {
    const uint32_t n_head_kv = this->n_head_kv(il);

    return n_embd_head_v * n_head_kv;
}

bool llama_hparams::is_n_embd_k_gqa_variable() const {
    const uint32_t val = n_embd_k_gqa();
    for (uint32_t il = 0; il < n_layer; ++il) {
        if (val != n_embd_k_gqa(il)) {
            return true;
        }
    }

    return false;
}

bool llama_hparams::is_n_embd_v_gqa_variable() const {
    const uint32_t val = n_embd_v_gqa();
    for (uint32_t il = 0; il < n_layer; ++il) {
        if (val != n_embd_v_gqa(il)) {
            return true;
        }
    }

    return false;
}

uint32_t llama_hparams::n_embd_k_gqa_max() const {
    uint32_t val = n_embd_k_gqa();
    for (uint32_t il = 0; il < n_layer; ++il) {
        val = std::max(val, n_embd_k_gqa(il));
    }

    return val;
}

uint32_t llama_hparams::n_embd_v_gqa_max() const {
    uint32_t val = n_embd_v_gqa();
    for (uint32_t il = 0; il < n_layer; ++il) {
        val = std::max(val, n_embd_v_gqa(il));
    }

    return val;
}

uint32_t llama_hparams::n_embd_r() const {
    if (wkv_head_size != 0) {
        // for RWKV models
        return token_shift_count * n_embd;
    }

    if (n_shortconv_l_cache != 0) {
        // for LFM2 models
        return n_embd * (n_shortconv_l_cache - 1);
    }

    // TODO: maybe support other convolution strides than 1
    // NOTE: since the first column of the conv_state is shifted out each time, it's not actually needed
    // Corresponds to Mamba's conv_states size
    return (ssm_d_conv > 0 ? ssm_d_conv - 1 : 0) * (ssm_d_inner + 2*ssm_n_group*ssm_d_state);
}

uint32_t llama_hparams::n_embd_s() const {
    if (wkv_head_size != 0) {
        // corresponds to RWKV's wkv_states size
        return n_embd * wkv_head_size;
    }

    // corresponds to Mamba's ssm_states size
    return ssm_d_state * ssm_d_inner;
}

bool llama_hparams::is_recurrent(uint32_t il) const {
    return recurrent_layer_arr[il];
}

uint32_t llama_hparams::n_pos_per_embd() const {
    return rope_type == LLAMA_ROPE_TYPE_MROPE ? 4 : 1;
}

bool llama_hparams::is_swa(uint32_t il) const {
    if (il < n_layer) {
        return swa_layers[il];
    }

    GGML_ABORT("fatal error");
}