klue-roberta-base-ner / config.json
jaehyeong.an
init klue-ner
5bded90
{
"_name_or_path": "klue/roberta-base",
"architectures": [
"RobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "B-DT",
"1": "I-DT",
"2": "B-LC",
"3": "I-LC",
"4": "B-OG",
"5": "I-OG",
"6": "B-PS",
"7": "I-PS",
"8": "B-QT",
"9": "I-QT",
"10": "B-TI",
"11": "I-TI",
"12": "O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-DT": 0,
"B-LC": 2,
"B-OG": 4,
"B-PS": 6,
"B-QT": 8,
"B-TI": 10,
"I-DT": 1,
"I-LC": 3,
"I-OG": 5,
"I-PS": 7,
"I-QT": 9,
"I-TI": 11,
"O": 12
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"tokenizer_class": "BertTokenizer",
"torch_dtype": "float32",
"transformers_version": "4.24.0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 32000
}