{ "_name_or_path": "bert-base-uncased", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "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", "problem_type": "single_label_classification", "pruned_heads": { "0": [ 0, 3, 6, 7, 8 ], "1": [ 8, 9 ], "2": [ 5 ], "3": [ 1, 11 ], "4": [ 9, 11, 6, 7 ], "5": [ 1, 11, 6, 7 ], "6": [ 9, 10, 3, 6 ], "7": [ 0, 2, 3, 7 ], "8": [ 0, 1, 2, 3, 5, 6, 9 ], "9": [ 1, 9 ], "10": [ 1, 2, 4, 5, 9 ], "11": [ 11, 6, 7 ] }, "torch_dtype": "float32", "transformers_version": "4.24.0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 }