ner-education-hcmut / config.json
trickstar0's picture
Training in progress, step 500
960e74d verified
raw
history blame
1.28 kB
{
"_name_or_path": "NlpHUST/ner-vietnamese-electra-base",
"architectures": [
"ElectraForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"embedding_size": 768,
"finetuning_task": "ner",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "B-LOCATION",
"1": "B-MISCELLANEOUS",
"2": "B-ORGANIZATION",
"3": "B-PERSON",
"4": "I-LOCATION",
"5": "I-MISCELLANEOUS",
"6": "I-ORGANIZATION",
"7": "I-PERSON",
"8": "O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-LOCATION": 0,
"B-MISCELLANEOUS": 1,
"B-ORGANIZATION": 2,
"B-PERSON": 3,
"I-LOCATION": 4,
"I-MISCELLANEOUS": 5,
"I-ORGANIZATION": 6,
"I-PERSON": 7,
"O": 8
},
"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",
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"summary_type": "first",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.42.4",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 62000
}