{ "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "dtype": "float32", "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "biology", "1": "business", "2": "chemistry", "3": "computer science", "4": "economics", "5": "engineering", "6": "health", "7": "history", "8": "law", "9": "math", "10": "other", "11": "philosophy", "12": "physics", "13": "psychology" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "biology": 0, "business": 1, "chemistry": 2, "computer science": 3, "economics": 4, "engineering": 5, "health": 6, "history": 7, "law": 8, "math": 9, "other": 10, "philosophy": 11, "physics": 12, "psychology": 13 }, "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", "transformers_version": "4.57.1", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 }