{ "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "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, "num_labels": 2, "output_attentions": false, "output_hidden_states": false, "torch_dtype": "float32", "transformers_version": "4.5.1", "vocab_size": 30522 }