mengzhouxia commited on
Commit
8a8379d
1 Parent(s): b71428a

first commit

Browse files
Files changed (4) hide show
  1. config.json +195 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +1 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/n/fs/nlp-mengzhou/space2/out/RTE/CoFi-test-v3/RTE_sparsity0.95_reglr0.01_ce0.1_layerdistillv4/best",
3
+ "architectures": [
4
+ "CoFiBertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "do_layer_distill": true,
9
+ "finetuning_task": "rte",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "0": 0,
18
+ "1": 1
19
+ },
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
+ 1,
32
+ 2,
33
+ 4,
34
+ 5,
35
+ 6,
36
+ 7,
37
+ 8,
38
+ 9,
39
+ 11
40
+ ],
41
+ "1": [
42
+ 0,
43
+ 1,
44
+ 2,
45
+ 3,
46
+ 4,
47
+ 5,
48
+ 6,
49
+ 7,
50
+ 8,
51
+ 9,
52
+ 10,
53
+ 11
54
+ ],
55
+ "2": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 4,
60
+ 5,
61
+ 7,
62
+ 8,
63
+ 9,
64
+ 10,
65
+ 11
66
+ ],
67
+ "3": [
68
+ 1,
69
+ 2,
70
+ 3,
71
+ 4,
72
+ 6,
73
+ 7,
74
+ 8,
75
+ 9,
76
+ 10,
77
+ 11
78
+ ],
79
+ "4": [
80
+ 0,
81
+ 1,
82
+ 2,
83
+ 3,
84
+ 4,
85
+ 5,
86
+ 6,
87
+ 7,
88
+ 8,
89
+ 9,
90
+ 10,
91
+ 11
92
+ ],
93
+ "5": [
94
+ 0,
95
+ 1,
96
+ 3,
97
+ 4,
98
+ 5,
99
+ 6,
100
+ 7,
101
+ 9,
102
+ 10,
103
+ 11
104
+ ],
105
+ "6": [
106
+ 0,
107
+ 1,
108
+ 2,
109
+ 3,
110
+ 4,
111
+ 5,
112
+ 6,
113
+ 7,
114
+ 8,
115
+ 9,
116
+ 10,
117
+ 11
118
+ ],
119
+ "7": [
120
+ 0,
121
+ 1,
122
+ 2,
123
+ 3,
124
+ 4,
125
+ 5,
126
+ 6,
127
+ 7,
128
+ 8,
129
+ 9,
130
+ 10,
131
+ 11
132
+ ],
133
+ "8": [
134
+ 0,
135
+ 1,
136
+ 2,
137
+ 3,
138
+ 4,
139
+ 5,
140
+ 6,
141
+ 7,
142
+ 8,
143
+ 9,
144
+ 10,
145
+ 11
146
+ ],
147
+ "9": [
148
+ 0,
149
+ 1,
150
+ 2,
151
+ 3,
152
+ 4,
153
+ 5,
154
+ 6,
155
+ 7,
156
+ 8,
157
+ 9,
158
+ 10,
159
+ 11
160
+ ],
161
+ "10": [
162
+ 0,
163
+ 1,
164
+ 2,
165
+ 3,
166
+ 4,
167
+ 5,
168
+ 6,
169
+ 7,
170
+ 8,
171
+ 9,
172
+ 10,
173
+ 11
174
+ ],
175
+ "11": [
176
+ 0,
177
+ 1,
178
+ 2,
179
+ 3,
180
+ 4,
181
+ 5,
182
+ 6,
183
+ 7,
184
+ 8,
185
+ 9,
186
+ 10,
187
+ 11
188
+ ]
189
+ },
190
+ "torch_dtype": "float32",
191
+ "transformers_version": "4.17.0.dev0",
192
+ "type_vocab_size": 2,
193
+ "use_cache": true,
194
+ "vocab_size": 30522
195
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abab7fb083675c103ea334acaccb21e749d4776052f660e5928af4a000ad1ab5
3
+ size 112776873
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, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff