Hyun9junn commited on
Commit
6d53e29
·
verified ·
1 Parent(s): facee65

Add config.json

Browse files
Files changed (1) hide show
  1. config.json +230 -0
config.json ADDED
@@ -0,0 +1,230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ExaoneMoeForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 53,
9
+ "first_k_dense_replace": 1,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 6144,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 18432,
15
+ "is_moe_layer": [
16
+ false,
17
+ true,
18
+ true,
19
+ true,
20
+ true,
21
+ true,
22
+ true,
23
+ true,
24
+ true,
25
+ true,
26
+ true,
27
+ true,
28
+ true,
29
+ true,
30
+ true,
31
+ true,
32
+ true,
33
+ true,
34
+ true,
35
+ true,
36
+ true,
37
+ true,
38
+ true,
39
+ true,
40
+ true,
41
+ true,
42
+ true,
43
+ true,
44
+ true,
45
+ true,
46
+ true,
47
+ true,
48
+ true,
49
+ true,
50
+ true,
51
+ true,
52
+ true,
53
+ true,
54
+ true,
55
+ true,
56
+ true,
57
+ true,
58
+ true,
59
+ true,
60
+ true,
61
+ true,
62
+ true,
63
+ true
64
+ ],
65
+ "layer_types": [
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "full_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "full_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "full_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "full_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "full_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "full_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "full_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "full_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "sliding_attention",
101
+ "full_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "full_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "full_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "sliding_attention",
113
+ "full_attention"
114
+ ],
115
+ "max_position_embeddings": 262144,
116
+ "mlp_layer_types": [
117
+ "dense",
118
+ "sparse",
119
+ "sparse",
120
+ "sparse",
121
+ "sparse",
122
+ "sparse",
123
+ "sparse",
124
+ "sparse",
125
+ "sparse",
126
+ "sparse",
127
+ "sparse",
128
+ "sparse",
129
+ "sparse",
130
+ "sparse",
131
+ "sparse",
132
+ "sparse",
133
+ "sparse",
134
+ "sparse",
135
+ "sparse",
136
+ "sparse",
137
+ "sparse",
138
+ "sparse",
139
+ "sparse",
140
+ "sparse",
141
+ "sparse",
142
+ "sparse",
143
+ "sparse",
144
+ "sparse",
145
+ "sparse",
146
+ "sparse",
147
+ "sparse",
148
+ "sparse",
149
+ "sparse",
150
+ "sparse",
151
+ "sparse",
152
+ "sparse",
153
+ "sparse",
154
+ "sparse",
155
+ "sparse",
156
+ "sparse",
157
+ "sparse",
158
+ "sparse",
159
+ "sparse",
160
+ "sparse",
161
+ "sparse",
162
+ "sparse",
163
+ "sparse",
164
+ "sparse"
165
+ ],
166
+ "model_type": "exaone_moe",
167
+ "moe_intermediate_size": 2048,
168
+ "n_group": 1,
169
+ "norm_topk_prob": true,
170
+ "num_attention_heads": 64,
171
+ "num_experts": 128,
172
+ "num_experts_per_tok": 8,
173
+ "num_hidden_layers": 48,
174
+ "num_key_value_heads": 8,
175
+ "num_nextn_predict_layers": 1,
176
+ "num_shared_experts": 1,
177
+ "pad_token_id": 0,
178
+ "quantization_config": {
179
+ "config_groups": {
180
+ "group_0": {
181
+ "format": "pack-quantized",
182
+ "input_activations": null,
183
+ "output_activations": null,
184
+ "targets": [
185
+ "Linear"
186
+ ],
187
+ "weights": {
188
+ "actorder": null,
189
+ "block_structure": null,
190
+ "dynamic": false,
191
+ "group_size": 128,
192
+ "num_bits": 4,
193
+ "observer": "memoryless_minmax",
194
+ "observer_kwargs": {},
195
+ "scale_dtype": null,
196
+ "strategy": "group",
197
+ "symmetric": true,
198
+ "type": "int",
199
+ "zp_dtype": null
200
+ }
201
+ }
202
+ },
203
+ "format": "pack-quantized",
204
+ "global_compression_ratio": null,
205
+ "ignore": [
206
+ "lm_head"
207
+ ],
208
+ "kv_cache_scheme": null,
209
+ "quant_method": "compressed-tensors",
210
+ "quantization_status": "compressed",
211
+ "sparsity_config": {},
212
+ "transform_config": {},
213
+ "version": "0.15.0"
214
+ },
215
+ "rms_norm_eps": 1e-05,
216
+ "rope_parameters": {
217
+ "rope_theta": 1000000,
218
+ "rope_type": "default"
219
+ },
220
+ "routed_scaling_factor": 2.5,
221
+ "scoring_func": "sigmoid",
222
+ "sliding_window": 128,
223
+ "sliding_window_pattern": "LLLG",
224
+ "tie_word_embeddings": false,
225
+ "tokenizer_class": "GPT2Tokenizer",
226
+ "topk_group": 1,
227
+ "transformers_version": "5.5.0",
228
+ "use_cache": true,
229
+ "vocab_size": 153600
230
+ }