| { | |
| "_name_or_path": "bert-base-uncased", | |
| "adapters": { | |
| "adapters": { | |
| "squad": "b1017368d7a97b11" | |
| }, | |
| "config_map": { | |
| "b1017368d7a97b11": { | |
| "adapter_residual_before_ln": false, | |
| "cross_adapter": false, | |
| "inv_adapter": null, | |
| "inv_adapter_reduction_factor": null, | |
| "leave_out": [], | |
| "ln_after": false, | |
| "ln_before": false, | |
| "mh_adapter": true, | |
| "non_linearity": "swish", | |
| "original_ln_after": true, | |
| "original_ln_before": false, | |
| "output_adapter": true, | |
| "reduction_factor": 16, | |
| "residual_before_ln": true | |
| } | |
| } | |
| }, | |
| "architectures": [ | |
| "BertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "transformers_version": "2.1.0a0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 30522 | |
| } | |