{ "architectures": [ "MultiHeadStmtClassifier" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "dtype": "float32", "gate1_loss_weight": 1.0, "gate2_loss_weight": 1.0, "gate2_num_labels": 20, "gate3_loss_weight": 1.0, "gate3_num_labels": 26, "gate4_loss_weight": 1.0, "gate4_num_labels": 3, "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": "4.56.1", "type_vocab_size": 2, "use_cache": true, "vocab_size": 28897 }