bert-finetuned-ner / config.json
airi's picture
Training in progress, epoch 1
e826c86
raw
history blame
1.25 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-PER",
"2": "I-PER",
"3": "B-ORG",
"4": "I-ORG",
"5": "B-LOC",
"6": "I-LOC",
"7": "B-MISC",
"8": "I-MISC"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-LOC": "5",
"B-MISC": "7",
"B-ORG": "3",
"B-PER": "1",
"I-LOC": "6",
"I-MISC": "8",
"I-ORG": "4",
"I-PER": "2",
"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": "4.18.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}