{ "_name_or_path": "cl-tohoku/bert-base-japanese-v3", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "Task_Solution", "1": "Creative_Generation", "2": "Knowledge_Explanation", "3": "Analytical_Reasoning", "4": "Information_Extraction", "5": "Simple_Fact_Checking", "6": "Step_by_Step_Calculation", "7": "Comparison_Similarity", "8": "Role_Play_Response", "9": "Opinion_Perspective" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "Analytical_Reasoning": 3, "Comparison_Similarity": 7, "Creative_Generation": 1, "Information_Extraction": 4, "Knowledge_Explanation": 2, "Opinion_Perspective": 9, "Role_Play_Response": 8, "Simple_Fact_Checking": 5, "Step_by_Step_Calculation": 6, "Task_Solution": 0 }, "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", "torch_dtype": "float32", "transformers_version": "4.46.3", "type_vocab_size": 2, "use_cache": true, "vocab_size": 32768 }