VBHC-classify / config.json
hoang.dang1
update
824ead0
{
"_name_or_path": "NlpHUST/electra-base-vn",
"architectures": [
"ElectraForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"embedding_size": 768,
"finetuning_task": "text-classification",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "B\u00e1o c\u00e1o",
"1": "Ch\u1ec9 th\u1ecb",
"2": "C\u00f4ng \u0111i\u1ec7n",
"3": "H\u01b0\u1edbng d\u1eabn",
"4": "K\u1ebf ho\u1ea1ch",
"5": "Lu\u1eadt",
"6": "Ngh\u1ecb quy\u1ebft",
"7": "Ngh\u1ecb \u0111\u1ecbnh",
"8": "Quy ch\u1ebf",
"9": "Quy \u0111\u1ecbnh",
"10": "Quy\u1ebft \u0111\u1ecbnh",
"11": "Th\u00f4ng b\u00e1o",
"12": "Th\u00f4ng t\u01b0",
"13": "Th\u00f4ng t\u01b0 li\u00ean t\u1ecbch",
"14": "V\u0103n b\u1ea3n kh\u00e1c",
"15": "\u0110i\u1ec1u \u01b0\u1edbc qu\u1ed1c t\u1ebf"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B\u00e1o c\u00e1o": 0,
"Ch\u1ec9 th\u1ecb": 1,
"C\u00f4ng \u0111i\u1ec7n": 2,
"H\u01b0\u1edbng d\u1eabn": 3,
"K\u1ebf ho\u1ea1ch": 4,
"Lu\u1eadt": 5,
"Ngh\u1ecb quy\u1ebft": 6,
"Ngh\u1ecb \u0111\u1ecbnh": 7,
"Quy ch\u1ebf": 8,
"Quy \u0111\u1ecbnh": 9,
"Quy\u1ebft \u0111\u1ecbnh": 10,
"Th\u00f4ng b\u00e1o": 11,
"Th\u00f4ng t\u01b0": 12,
"Th\u00f4ng t\u01b0 li\u00ean t\u1ecbch": 13,
"V\u0103n b\u1ea3n kh\u00e1c": 14,
"\u0110i\u1ec1u \u01b0\u1edbc qu\u1ed1c t\u1ebf": 15
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "electra",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"summary_type": "first",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 62000
}