Hugging Face's logo

PowerServe
/
Llama-3.1-8B-PowerServe-Speculate-QNN29-8G4

GGUF
Inference Endpoints
conversational
Model card Files Community
Llama-3.1-8B-PowerServe-Speculate-QNN29-8G4
File size: 3,770 Bytes 
442514a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "model_parameters": {
    "n_layers": 32,
    "vocab_size": 128256,
    "embed_dim": 4096,
    "ffn_hidden_dim": 14336,
    "head_dim": 128,
    "n_kv_heads": 8,
    "rope_theta": 500000.0,
    "rms_norm_eps": 1e-05,
    "attention_mask_value": -100000.0,
    "tie_embedding": false
  },
  "qnn_parameters": {
    "n_hvx_threads": 4
  },
  "graphs": [
    {
      "type": "transformers",
      "start_layer_id": 0,
      "end_layer_id": 8,
      "batch_size": 16,
      "cache_size": 1920,
      "context_size": 2048,
      "graph_name": "batch_16",
      "model_path": "llama3_1_8b_0.bin",
      "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
      "kv_size": 13,
      "x_name": "x",
      "out_name": "out"
    },
    {
      "type": "transformers",
      "start_layer_id": 8,
      "end_layer_id": 16,
      "batch_size": 16,
      "cache_size": 1920,
      "context_size": 2048,
      "graph_name": "batch_16",
      "model_path": "llama3_1_8b_1.bin",
      "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
      "kv_size": 13,
      "x_name": "x",
      "out_name": "out"
    },
    {
      "type": "transformers",
      "start_layer_id": 16,
      "end_layer_id": 24,
      "batch_size": 16,
      "cache_size": 1920,
      "context_size": 2048,
      "graph_name": "batch_16",
      "model_path": "llama3_1_8b_2.bin",
      "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
      "kv_size": 13,
      "x_name": "x",
      "out_name": "out"
    },
    {
      "type": "transformers",
      "start_layer_id": 24,
      "end_layer_id": 32,
      "batch_size": 16,
      "cache_size": 1920,
      "context_size": 2048,
      "graph_name": "batch_16",
      "model_path": "llama3_1_8b_3.bin",
      "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
      "kv_size": 13,
      "x_name": "x",
      "out_name": "out"
    },
    {
      "type": "transformers",
      "start_layer_id": 0,
      "end_layer_id": 8,
      "batch_size": 128,
      "cache_size": 1920,
      "context_size": 2048,
      "graph_name": "batch_128",
      "model_path": "llama3_1_8b_0.bin",
      "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
      "kv_size": 13,
      "x_name": "x",
      "out_name": "out"
    },
    {
      "type": "transformers",
      "start_layer_id": 8,
      "end_layer_id": 16,
      "batch_size": 128,
      "cache_size": 1920,
      "context_size": 2048,
      "graph_name": "batch_128",
      "model_path": "llama3_1_8b_1.bin",
      "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
      "kv_size": 13,
      "x_name": "x",
      "out_name": "out"
    },
    {
      "type": "transformers",
      "start_layer_id": 16,
      "end_layer_id": 24,
      "batch_size": 128,
      "cache_size": 1920,
      "context_size": 2048,
      "graph_name": "batch_128",
      "model_path": "llama3_1_8b_2.bin",
      "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
      "kv_size": 13,
      "x_name": "x",
      "out_name": "out"
    },
    {
      "type": "transformers",
      "start_layer_id": 24,
      "end_layer_id": 32,
      "batch_size": 128,
      "cache_size": 1920,
      "context_size": 2048,
      "graph_name": "batch_128",
      "model_path": "llama3_1_8b_3.bin",
      "kv_path_format": "kv/layer_{layer_id}_{kv_type}_{head_id}.raw",
      "kv_size": 13,
      "x_name": "x",
      "out_name": "out"
    }
  ],
  "embeddings": [
    {
      "graph_name": "batch_16",
      "model_path": "lm_head.bin",
      "batch_size": 16,
      "x_name": "x",
      "out_name": "logits"
    },
    {
      "graph_name": "batch_128",
      "model_path": "lm_head.bin",
      "batch_size": 128,
      "x_name": "x",
      "out_name": "logits"
    }
  ]
}