1
{
2
  "activation": "gelu",
3
  "architectures": [
4
    "DistilBertForMaskedLM"
5
  ],
6
  "attention_dropout": 0.1,
7
  "dim": 768,
8
  "dropout": 0.1,
9
  "hidden_dim": 3072,
10
  "initializer_range": 0.02,
11
  "max_position_embeddings": 512,
12
  "model_type": "distilbert",
13
  "n_heads": 12,
14
  "n_layers": 6,
15
  "pad_token_id": 0,
16
  "qa_dropout": 0.1,
17
  "seq_classif_dropout": 0.2,
18
  "sinusoidal_pos_embds": false,
19
  "tie_weights_": true,
20
  "transformers_version": "4.10.0.dev0",
21
  "vocab_size": 30522
22
}
23