mengzhouxia commited on
Commit
2d91504
1 Parent(s): 7cd9280

first commit

Browse files
Files changed (4) hide show
  1. config.json +188 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +1 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/checkpoint/mengzhouxia/space2/out/squad/layerdistillv3_prunehidden/squad_l0_headint_nosvd_layerpuning_layerdistillv3_prunehidden_seed57_distilltemp2_pretrain6000_warpup12000_ts0.93_cealpha0.1_20epochs/best",
3
+ "architectures": [
4
+ "NewBertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "decompose_qk": false,
8
+ "decompose_vo": false,
9
+ "do_distill": true,
10
+ "do_emb_distill": false,
11
+ "do_layer_distill": true,
12
+ "do_mha_distill": false,
13
+ "do_mha_layer_distill": false,
14
+ "gradient_checkpointing": false,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "output_attentions": true,
26
+ "output_hidden_states": true,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "pruned_heads": {
30
+ "0": [
31
+ 0,
32
+ 1,
33
+ 2,
34
+ 4,
35
+ 5,
36
+ 6,
37
+ 7,
38
+ 8,
39
+ 9,
40
+ 11
41
+ ],
42
+ "1": [
43
+ 0,
44
+ 1,
45
+ 2,
46
+ 3,
47
+ 5,
48
+ 6,
49
+ 7,
50
+ 8,
51
+ 9
52
+ ],
53
+ "2": [
54
+ 1,
55
+ 2,
56
+ 3,
57
+ 4,
58
+ 5,
59
+ 7,
60
+ 8,
61
+ 9,
62
+ 10,
63
+ 11
64
+ ],
65
+ "3": [
66
+ 1,
67
+ 2,
68
+ 3,
69
+ 4,
70
+ 5,
71
+ 6,
72
+ 7,
73
+ 9,
74
+ 10,
75
+ 11
76
+ ],
77
+ "4": [
78
+ 0,
79
+ 1,
80
+ 2,
81
+ 3,
82
+ 4,
83
+ 5,
84
+ 6,
85
+ 7,
86
+ 8,
87
+ 9,
88
+ 10,
89
+ 11
90
+ ],
91
+ "5": [
92
+ 0,
93
+ 1,
94
+ 2,
95
+ 3,
96
+ 4,
97
+ 5,
98
+ 6,
99
+ 7,
100
+ 11
101
+ ],
102
+ "6": [
103
+ 0,
104
+ 1,
105
+ 2,
106
+ 3,
107
+ 4,
108
+ 5,
109
+ 6,
110
+ 7,
111
+ 8,
112
+ 9,
113
+ 10,
114
+ 11
115
+ ],
116
+ "7": [
117
+ 1,
118
+ 2,
119
+ 3,
120
+ 5,
121
+ 6,
122
+ 7,
123
+ 8,
124
+ 9,
125
+ 10,
126
+ 11
127
+ ],
128
+ "8": [
129
+ 1,
130
+ 2,
131
+ 4,
132
+ 5,
133
+ 6,
134
+ 7,
135
+ 8,
136
+ 9,
137
+ 10,
138
+ 11
139
+ ],
140
+ "9": [
141
+ 0,
142
+ 1,
143
+ 2,
144
+ 4,
145
+ 5,
146
+ 7,
147
+ 8,
148
+ 9,
149
+ 10,
150
+ 11
151
+ ],
152
+ "10": [
153
+ 0,
154
+ 1,
155
+ 2,
156
+ 3,
157
+ 4,
158
+ 5,
159
+ 6,
160
+ 7,
161
+ 8,
162
+ 9,
163
+ 10,
164
+ 11
165
+ ],
166
+ "11": [
167
+ 0,
168
+ 1,
169
+ 2,
170
+ 3,
171
+ 4,
172
+ 5,
173
+ 6,
174
+ 7,
175
+ 8,
176
+ 9,
177
+ 10,
178
+ 11
179
+ ]
180
+ },
181
+ "qk_denominator": "ori",
182
+ "sephidden_pruned": false,
183
+ "transform_embedding": false,
184
+ "transformers_version": "4.3.2",
185
+ "type_vocab_size": 2,
186
+ "use_cache": true,
187
+ "vocab_size": 30522
188
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b155e45fd2268e0d59e79d6b38824ef7539fabfc1e1b0d76fac88c30faff8b2d
3
+ size 123145571
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff