bert_cn_finetuning / config.json
1
{
2
  "architectures": [
3
    "BertForMaskedLM"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "directionality": "bidi",
7
  "finetuning_task": "sst-2",
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
11
  "id2label": {
12
    "0": "LABEL_0",
13
    "1": "LABEL_1"
14
  },
15
  "initializer_range": 0.02,
16
  "intermediate_size": 3072,
17
  "is_decoder": false,
18
  "label2id": {
19
    "LABEL_0": 0,
20
    "LABEL_1": 1
21
  },
22
  "layer_norm_eps": 1e-12,
23
  "max_position_embeddings": 512,
24
  "model_type": "bert",
25
  "num_attention_heads": 12,
26
  "num_hidden_layers": 12,
27
  "num_labels": 2,
28
  "output_attentions": false,
29
  "output_hidden_states": false,
30
  "output_past": true,
31
  "pad_token_id": 0,
32
  "pooler_fc_size": 768,
33
  "pooler_num_attention_heads": 12,
34
  "pooler_num_fc_layers": 3,
35
  "pooler_size_per_head": 128,
36
  "pooler_type": "first_token_transform",
37
  "pruned_heads": {},
38
  "torchscript": false,
39
  "type_vocab_size": 2,
40
  "use_bfloat16": false,
41
  "vocab_size": 21128
42
}
43