{ "_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, "id2label": { "0": "boolq", "1": "commonsense_qa", "2": "drop", "3": "duorc", "4": "hellaswag", "5": "hotpot_qa", "6": "hybrid_qa", "7": "narrativeqa", "8": "natural_questions", "9": "newsqa", "10": "biu-nlp/qamr", "11": "race", "12": "search_qa", "13": "social_i_qa", "14": "squad", "15": "trivia_qa" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "boolq": 0, "commonsense_qa": 1, "biu-nlp/qamr": 10, "race": 11, "search_qa": 12, "social_i_qa": 13, "squad": 14, "trivia_qa": 15, "drop": 2, "duorc": 3, "hellaswag": 4, "hotpot_qa": 5, "hybrid_qa": 6, "narrativeqa": 7, "natural_questions": 8, "newsqa": 9 }, "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", "torch_dtype": "float32", "transformers_version": "4.23.1", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 }