Hugging Face's logo

princeton-nlp
/
CoFi-MNLI-s95

Text Classification
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
1
mengzhouxia commited on
Commit
245aa5a
•
1 Parent(s): c5ca5f3

first commit

Browse files
Files changed (3) hide show
  1. config.json +199 -0
  2. pytorch_model.bin +3 -0
  3. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NewBertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "decompose_qk": false,
7
+ "decompose_vo": false,
8
+ "do_distill": true,
9
+ "do_emb_distill": false,
10
+ "do_layer_distill": true,
11
+ "do_mha_distill": false,
12
+ "do_mha_layer_distill": false,
13
+ "finetuning_task": "mnli",
14
+ "gradient_checkpointing": false,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "LABEL_0",
20
+ "1": "LABEL_1",
21
+ "2": "LABEL_2"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "output_attentions": true,
36
+ "output_hidden_states": true,
37
+ "pad_token_id": 0,
38
+ "pruned_heads": {
39
+ "0": [
40
+ 0,
41
+ 1,
42
+ 2,
43
+ 3,
44
+ 4,
45
+ 5,
46
+ 6,
47
+ 7,
48
+ 8,
49
+ 9,
50
+ 11
51
+ ],
52
+ "1": [
53
+ 0,
54
+ 2,
55
+ 3,
56
+ 5,
57
+ 6,
58
+ 7,
59
+ 8,
60
+ 9
61
+ ],
62
+ "2": [
63
+ 0,
64
+ 1,
65
+ 2,
66
+ 3,
67
+ 4,
68
+ 5,
69
+ 7,
70
+ 8,
71
+ 10,
72
+ 11
73
+ ],
74
+ "3": [
75
+ 0,
76
+ 1,
77
+ 2,
78
+ 3,
79
+ 4,
80
+ 5,
81
+ 6,
82
+ 7,
83
+ 8,
84
+ 9,
85
+ 10,
86
+ 11
87
+ ],
88
+ "4": [
89
+ 0,
90
+ 1,
91
+ 2,
92
+ 3,
93
+ 4,
94
+ 5,
95
+ 6,
96
+ 7,
97
+ 8,
98
+ 9,
99
+ 10,
100
+ 11
101
+ ],
102
+ "5": [
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
+ "6": [
117
+ 0,
118
+ 1,
119
+ 2,
120
+ 3,
121
+ 4,
122
+ 5,
123
+ 6,
124
+ 7,
125
+ 8,
126
+ 9,
127
+ 10,
128
+ 11
129
+ ],
130
+ "7": [
131
+ 0,
132
+ 1,
133
+ 2,
134
+ 3,
135
+ 4,
136
+ 5,
137
+ 6,
138
+ 7,
139
+ 8,
140
+ 9,
141
+ 10,
142
+ 11
143
+ ],
144
+ "8": [
145
+ 0,
146
+ 1,
147
+ 2,
148
+ 3,
149
+ 4,
150
+ 6,
151
+ 7,
152
+ 8,
153
+ 10,
154
+ 11
155
+ ],
156
+ "9": [
157
+ 0,
158
+ 1,
159
+ 2,
160
+ 3,
161
+ 4,
162
+ 5,
163
+ 6,
164
+ 7,
165
+ 9
166
+ ],
167
+ "10": [
168
+ 0,
169
+ 1,
170
+ 2,
171
+ 4,
172
+ 5,
173
+ 6,
174
+ 7,
175
+ 8,
176
+ 9,
177
+ 10
178
+ ],
179
+ "11": [
180
+ 0,
181
+ 1,
182
+ 2,
183
+ 3,
184
+ 4,
185
+ 5,
186
+ 6,
187
+ 7,
188
+ 8,
189
+ 9,
190
+ 10,
191
+ 11
192
+ ]
193
+ },
194
+ "qk_denominator": "ori",
195
+ "sephidden_pruned": false,
196
+ "transform_embedding": false,
197
+ "type_vocab_size": 2,
198
+ "vocab_size": 30522
199
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3dc305e6d3ed75c2108e0bf35ff3db58cdb70c25f875a6287f9931d0b1b27bb
3
+ size 116937319
vocab.txt ADDED
The diff for this file is too large to render. See raw diff