AptaArkana's picture
Training complete
da70a53 verified
raw
history blame
2.31 kB
{
"_name_or_path": "Davlan/bert-base-multilingual-cased-ner-hrl",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-CRD",
"2": "I-CRD",
"3": "B-DAT",
"4": "I-DAT",
"5": "B-EVT",
"6": "I-EVT",
"7": "B-FAC",
"8": "I-FAC",
"9": "B-GPE",
"10": "I-GPE",
"11": "B-LAN",
"12": "I-LAN",
"13": "B-LAW",
"14": "I-LAW",
"15": "B-LOC",
"16": "I-LOC",
"17": "B-MON",
"18": "I-MON",
"19": "B-NOR",
"20": "I-NOR",
"21": "B-ORD",
"22": "I-ORD",
"23": "B-ORG",
"24": "I-ORG",
"25": "B-PER",
"26": "I-PER",
"27": "B-PRC",
"28": "I-PRC",
"29": "B-PRD",
"30": "I-PRD",
"31": "B-QTY",
"32": "I-QTY",
"33": "B-REG",
"34": "I-REG",
"35": "B-TIM",
"36": "I-TIM",
"37": "B-WOA",
"38": "I-WOA"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-CRD": 1,
"B-DAT": 3,
"B-EVT": 5,
"B-FAC": 7,
"B-GPE": 9,
"B-LAN": 11,
"B-LAW": 13,
"B-LOC": 15,
"B-MON": 17,
"B-NOR": 19,
"B-ORD": 21,
"B-ORG": 23,
"B-PER": 25,
"B-PRC": 27,
"B-PRD": 29,
"B-QTY": 31,
"B-REG": 33,
"B-TIM": 35,
"B-WOA": 37,
"I-CRD": 2,
"I-DAT": 4,
"I-EVT": 6,
"I-FAC": 8,
"I-GPE": 10,
"I-LAN": 12,
"I-LAW": 14,
"I-LOC": 16,
"I-MON": 18,
"I-NOR": 20,
"I-ORD": 22,
"I-ORG": 24,
"I-PER": 26,
"I-PRC": 28,
"I-PRD": 30,
"I-QTY": 32,
"I-REG": 34,
"I-TIM": 36,
"I-WOA": 38,
"O": 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,
"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",
"torch_dtype": "float32",
"transformers_version": "4.37.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}