config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "BertForMaskedLM" |
| 4 | ], |
| 5 | "attention_probs_dropout_prob": 0.1, |
| 6 | "directionality": "bidi", |
| 7 | "hidden_act": "gelu", |
| 8 | "hidden_dropout_prob": 0.1, |
| 9 | "hidden_size": 768, |
| 10 | "initializer_range": 0.02, |
| 11 | "intermediate_size": 3072, |
| 12 | "layer_norm_eps": 1e-12, |
| 13 | "max_position_embeddings": 512, |
| 14 | "model_type": "bert", |
| 15 | "num_attention_heads": 12, |
| 16 | "num_hidden_layers": 12, |
| 17 | "pad_token_id": 0, |
| 18 | "pooler_fc_size": 768, |
| 19 | "pooler_num_attention_heads": 12, |
| 20 | "pooler_num_fc_layers": 3, |
| 21 | "pooler_size_per_head": 128, |
| 22 | "pooler_type": "first_token_transform", |
| 23 | "type_vocab_size": 2, |
| 24 | "vocab_size": 119547 |
| 25 | } |
| 26 | |