{"architectures": ["BertForSequenceClassification"], "hidden_size": 768, "num_attention_heads": 12, "num_hidden_layers": 12, "vocab_size": 30522, "type_vocab_size": 2, "max_position_embeddings": 512, "initializer_range": 0.02, "layer_norm_eps": 1e-12, "attention_probs_dropout_prob": 0.1, "hidden_dropout_prob": 0.1} |