File size: 9,383 Bytes
e48bc9d
c5c2ca6
e48bc9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
{
  "_name_or_path": "/slot/sandbox/j/_tmp/data4v0q57a2",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 8192,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quantization_config": {
    "in_group_size": 8,
    "linear_weights_not_to_quantize": [
      "model.layers.0.input_layernorm.weight",
      "model.layers.0.post_attention_layernorm.weight",
      "model.layers.1.input_layernorm.weight",
      "model.layers.1.post_attention_layernorm.weight",
      "model.layers.2.input_layernorm.weight",
      "model.layers.2.post_attention_layernorm.weight",
      "model.layers.3.input_layernorm.weight",
      "model.layers.3.post_attention_layernorm.weight",
      "model.layers.4.input_layernorm.weight",
      "model.layers.4.post_attention_layernorm.weight",
      "model.layers.5.input_layernorm.weight",
      "model.layers.5.post_attention_layernorm.weight",
      "model.layers.6.input_layernorm.weight",
      "model.layers.6.post_attention_layernorm.weight",
      "model.layers.7.input_layernorm.weight",
      "model.layers.7.post_attention_layernorm.weight",
      "model.layers.8.input_layernorm.weight",
      "model.layers.8.post_attention_layernorm.weight",
      "model.layers.9.input_layernorm.weight",
      "model.layers.9.post_attention_layernorm.weight",
      "model.layers.10.input_layernorm.weight",
      "model.layers.10.post_attention_layernorm.weight",
      "model.layers.11.input_layernorm.weight",
      "model.layers.11.post_attention_layernorm.weight",
      "model.layers.12.input_layernorm.weight",
      "model.layers.12.post_attention_layernorm.weight",
      "model.layers.13.input_layernorm.weight",
      "model.layers.13.post_attention_layernorm.weight",
      "model.layers.14.input_layernorm.weight",
      "model.layers.14.post_attention_layernorm.weight",
      "model.layers.15.input_layernorm.weight",
      "model.layers.15.post_attention_layernorm.weight",
      "model.layers.16.input_layernorm.weight",
      "model.layers.16.post_attention_layernorm.weight",
      "model.layers.17.input_layernorm.weight",
      "model.layers.17.post_attention_layernorm.weight",
      "model.layers.18.input_layernorm.weight",
      "model.layers.18.post_attention_layernorm.weight",
      "model.layers.19.input_layernorm.weight",
      "model.layers.19.post_attention_layernorm.weight",
      "model.layers.20.input_layernorm.weight",
      "model.layers.20.post_attention_layernorm.weight",
      "model.layers.21.input_layernorm.weight",
      "model.layers.21.post_attention_layernorm.weight",
      "model.layers.22.input_layernorm.weight",
      "model.layers.22.post_attention_layernorm.weight",
      "model.layers.23.input_layernorm.weight",
      "model.layers.23.post_attention_layernorm.weight",
      "model.layers.24.input_layernorm.weight",
      "model.layers.24.post_attention_layernorm.weight",
      "model.layers.25.input_layernorm.weight",
      "model.layers.25.post_attention_layernorm.weight",
      "model.layers.26.input_layernorm.weight",
      "model.layers.26.post_attention_layernorm.weight",
      "model.layers.27.input_layernorm.weight",
      "model.layers.27.post_attention_layernorm.weight",
      "model.layers.28.input_layernorm.weight",
      "model.layers.28.post_attention_layernorm.weight",
      "model.layers.29.input_layernorm.weight",
      "model.layers.29.post_attention_layernorm.weight",
      "model.layers.30.input_layernorm.weight",
      "model.layers.30.post_attention_layernorm.weight",
      "model.layers.31.input_layernorm.weight",
      "model.layers.31.post_attention_layernorm.weight",
      "model.layers.32.input_layernorm.weight",
      "model.layers.32.post_attention_layernorm.weight",
      "model.layers.33.input_layernorm.weight",
      "model.layers.33.post_attention_layernorm.weight",
      "model.layers.34.input_layernorm.weight",
      "model.layers.34.post_attention_layernorm.weight",
      "model.layers.35.input_layernorm.weight",
      "model.layers.35.post_attention_layernorm.weight",
      "model.layers.36.input_layernorm.weight",
      "model.layers.36.post_attention_layernorm.weight",
      "model.layers.37.input_layernorm.weight",
      "model.layers.37.post_attention_layernorm.weight",
      "model.layers.38.input_layernorm.weight",
      "model.layers.38.post_attention_layernorm.weight",
      "model.layers.39.input_layernorm.weight",
      "model.layers.39.post_attention_layernorm.weight",
      "model.layers.40.input_layernorm.weight",
      "model.layers.40.post_attention_layernorm.weight",
      "model.layers.41.input_layernorm.weight",
      "model.layers.41.post_attention_layernorm.weight",
      "model.layers.42.input_layernorm.weight",
      "model.layers.42.post_attention_layernorm.weight",
      "model.layers.43.input_layernorm.weight",
      "model.layers.43.post_attention_layernorm.weight",
      "model.layers.44.input_layernorm.weight",
      "model.layers.44.post_attention_layernorm.weight",
      "model.layers.45.input_layernorm.weight",
      "model.layers.45.post_attention_layernorm.weight",
      "model.layers.46.input_layernorm.weight",
      "model.layers.46.post_attention_layernorm.weight",
      "model.layers.47.input_layernorm.weight",
      "model.layers.47.post_attention_layernorm.weight",
      "model.layers.48.input_layernorm.weight",
      "model.layers.48.post_attention_layernorm.weight",
      "model.layers.49.input_layernorm.weight",
      "model.layers.49.post_attention_layernorm.weight",
      "model.layers.50.input_layernorm.weight",
      "model.layers.50.post_attention_layernorm.weight",
      "model.layers.51.input_layernorm.weight",
      "model.layers.51.post_attention_layernorm.weight",
      "model.layers.52.input_layernorm.weight",
      "model.layers.52.post_attention_layernorm.weight",
      "model.layers.53.input_layernorm.weight",
      "model.layers.53.post_attention_layernorm.weight",
      "model.layers.54.input_layernorm.weight",
      "model.layers.54.post_attention_layernorm.weight",
      "model.layers.55.input_layernorm.weight",
      "model.layers.55.post_attention_layernorm.weight",
      "model.layers.56.input_layernorm.weight",
      "model.layers.56.post_attention_layernorm.weight",
      "model.layers.57.input_layernorm.weight",
      "model.layers.57.post_attention_layernorm.weight",
      "model.layers.58.input_layernorm.weight",
      "model.layers.58.post_attention_layernorm.weight",
      "model.layers.59.input_layernorm.weight",
      "model.layers.59.post_attention_layernorm.weight",
      "model.layers.60.input_layernorm.weight",
      "model.layers.60.post_attention_layernorm.weight",
      "model.layers.61.input_layernorm.weight",
      "model.layers.61.post_attention_layernorm.weight",
      "model.layers.62.input_layernorm.weight",
      "model.layers.62.post_attention_layernorm.weight",
      "model.layers.63.input_layernorm.weight",
      "model.layers.63.post_attention_layernorm.weight",
      "model.layers.64.input_layernorm.weight",
      "model.layers.64.post_attention_layernorm.weight",
      "model.layers.65.input_layernorm.weight",
      "model.layers.65.post_attention_layernorm.weight",
      "model.layers.66.input_layernorm.weight",
      "model.layers.66.post_attention_layernorm.weight",
      "model.layers.67.input_layernorm.weight",
      "model.layers.67.post_attention_layernorm.weight",
      "model.layers.68.input_layernorm.weight",
      "model.layers.68.post_attention_layernorm.weight",
      "model.layers.69.input_layernorm.weight",
      "model.layers.69.post_attention_layernorm.weight",
      "model.layers.70.input_layernorm.weight",
      "model.layers.70.post_attention_layernorm.weight",
      "model.layers.71.input_layernorm.weight",
      "model.layers.71.post_attention_layernorm.weight",
      "model.layers.72.input_layernorm.weight",
      "model.layers.72.post_attention_layernorm.weight",
      "model.layers.73.input_layernorm.weight",
      "model.layers.73.post_attention_layernorm.weight",
      "model.layers.74.input_layernorm.weight",
      "model.layers.74.post_attention_layernorm.weight",
      "model.layers.75.input_layernorm.weight",
      "model.layers.75.post_attention_layernorm.weight",
      "model.layers.76.input_layernorm.weight",
      "model.layers.76.post_attention_layernorm.weight",
      "model.layers.77.input_layernorm.weight",
      "model.layers.77.post_attention_layernorm.weight",
      "model.layers.78.input_layernorm.weight",
      "model.layers.78.post_attention_layernorm.weight",
      "model.layers.79.input_layernorm.weight",
      "model.layers.79.post_attention_layernorm.weight",
      "model.embed_tokens.weight",
      "model.norm.weight",
      "lm_head.weight"
    ],
    "nbits_per_codebook": 16,
    "num_codebooks": 1,
    "out_group_size": 1,
    "quant_method": "aqlm"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.40.0.dev0",
  "use_cache": true,
  "vocab_size": 128256
}