{ "architectures": [ "BertForTokenClassification" ], "attention_probs_dropout_prob": 0.1, "directionality": "bidi", "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "O", "1": "ADJ", "2": "ADP", "3": "ADV", "4": "AUX", "5": "CONJ", "6": "DET", "7": "INTJ", "8": "NOUN", "9": "NUM", "10": "PART", "11": "PRON", "12": "PROPN", "13": "PUNCT", "14": "SCONJ", "15": "UNK", "16": "VERB", "17": "X" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "ADJ": 1, "ADP": 2, "ADV": 3, "AUX": 4, "CONJ": 5, "DET": 6, "INTJ": 7, "NOUN": 8, "NUM": 9, "O": 0, "PART": 10, "PRON": 11, "PROPN": 12, "PUNCT": 13, "SCONJ": 14, "UNK": 15, "VERB": 16, "X": 17 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "type_vocab_size": 2, "vocab_size": 119547 }