config.json
473 B · 23 lines · json Raw
1 {
2 "activation": "gelu",
3 "architectures": [
4 "DistilBertForQuestionAnswering"
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 "output_past": true,
16 "pad_token_id": 0,
17 "qa_dropout": 0.1,
18 "seq_classif_dropout": 0.2,
19 "sinusoidal_pos_embds": true,
20 "tie_weights_": true,
21 "vocab_size": 28996
22 }
23