1 {
2 "architectures": [
3 "BertForSequenceClassification"
4 ],
5 "attention_probs_dropout_prob": 0.1,
6 "gradient_checkpointing": false,
7 "hidden_act": "gelu",
8 "hidden_dropout_prob": 0.1,
9 "hidden_size": 768,
10 "id2label": {
11 "0": "LABEL_0",
12 "1": "LABEL_1",
13 "2": "LABEL_2",
14 "3": "LABEL_3",
15 "4": "LABEL_4",
16 "5": "LABEL_5",
17 "6": "LABEL_6",
18 "7": "LABEL_7",
19 "8": "LABEL_8"
20 },
21 "initializer_range": 0.02,
22 "intermediate_size": 3072,
23 "label2id": {
24 "LABEL_0": 0,
25 "LABEL_1": 1,
26 "LABEL_2": 2,
27 "LABEL_3": 3,
28 "LABEL_4": 4,
29 "LABEL_5": 5,
30 "LABEL_6": 6,
31 "LABEL_7": 7,
32 "LABEL_8": 8
33 },
34 "layer_norm_eps": 1e-12,
35 "max_position_embeddings": 512,
36 "model_type": "bert",
37 "num_attention_heads": 12,
38 "num_hidden_layers": 12,
39 "pad_token_id": 0,
40 "position_embedding_type": "absolute",
41 "transformers_version": "4.2.2",
42 "type_vocab_size": 2,
43 "use_cache": true,
44 "vocab_size": 32000
45 }
46