{ "_name_or_path": "AutoNLP", "_num_labels": 24, "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "directionality": "bidi", "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "1.0", "1": "10.0", "2": "11.0", "3": "12.0", "4": "13.0", "5": "14.0", "6": "15.0", "7": "16.0", "8": "17.0", "9": "18.0", "10": "19.0", "11": "2.0", "12": "20.0", "13": "21.0", "14": "22.0", "15": "23.0", "16": "24.0", "17": "3.0", "18": "4.0", "19": "5.0", "20": "6.0", "21": "7.0", "22": "8.0", "23": "9.0" }, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "1.0": 0, "10.0": 1, "11.0": 2, "12.0": 3, "13.0": 4, "14.0": 5, "15.0": 6, "16.0": 7, "17.0": 8, "18.0": 9, "19.0": 10, "2.0": 11, "20.0": 12, "21.0": 13, "22.0": 14, "23.0": 15, "24.0": 16, "3.0": 17, "4.0": 18, "5.0": 19, "6.0": 20, "7.0": 21, "8.0": 22, "9.0": 23 }, "layer_norm_eps": 1e-12, "max_length": 192, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 16, "num_hidden_layers": 24, "pad_token_id": 0, "padding": "max_length", "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "position_embedding_type": "absolute", "problem_type": "single_label_classification", "transformers_version": "4.8.0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 28996 }