{ "architectures": [ "BertForMaskedLM" ], "attention_probs_dropout_prob": 0.1, "directionality": "bidi", "finetuning_task": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "num_attention_heads": 16, "num_hidden_layers": 24, "num_labels": 2, "output_attentions": false, "output_hidden_states": false, "output_past": true, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "pruned_heads": {}, "torchscript": false, "type_vocab_size": 2, "use_bfloat16": false, "vocab_size": 29794 }