File size: 6,059 Bytes
f9ab186
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
{
  "_name_or_path": "/data5/models/Qwen2-57B-A14B-Instruct",
  "architectures": [
    "Qwen2MoeForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "decoder_sparse_step": 1,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "mlp_only_layers": [],
  "model_type": "qwen2_moe",
  "moe_intermediate_size": 2560,
  "norm_topk_prob": false,
  "num_attention_heads": 28,
  "num_experts": 64,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "output_router_logits": false,
  "quantization_config": {
    "amp": true,
    "autoround_version": "0.3.1.dev",
    "backend": "auto_round:gptq:exllamav2",
    "bits": 4,
    "data_type": "int",
    "dataset": "NeelNanda/pile-10k",
    "enable_minmax_tuning": true,
    "enable_norm_bias_tuning": false,
    "enable_quanted_input": true,
    "extra_config": {
      "model.layers.0.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.1.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.10.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.11.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.12.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.13.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.14.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.15.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.16.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.17.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.18.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.19.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.2.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.20.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.21.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.22.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.23.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.24.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.25.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.26.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.27.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.3.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.4.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.5.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.6.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.7.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.8.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      },
      "model.layers.9.mlp.shared_expert_gate": {
        "bits": 32,
        "data_type": "float",
        "group_size": null,
        "sym": null
      }
    },
    "gradient_accumulate_steps": 1,
    "group_size": 128,
    "iters": 1000,
    "low_gpu_mem_usage": false,
    "lr": 0.001,
    "minmax_lr": 0.001,
    "nsamples": 512,
    "quant_block_list": null,
    "quant_method": "intel/auto-round",
    "scale_dtype": "torch.float16",
    "seqlen": 2048,
    "sym": true,
    "train_bs": 8
  },
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "router_aux_loss_coef": 0.001,
  "shared_expert_intermediate_size": 20480,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}