bert-base-uncased / config.json
univanxx's picture
Training in progress, epoch 1
5db56e5
{
"_name_or_path": "bert-base-uncased",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "B-GPE",
"1": "B-LOC",
"2": "B-ORG",
"3": "B-VEH",
"4": "B-PER",
"5": "I-FAC",
"6": "I-VEH",
"7": "I-GPE",
"8": "B-FAC",
"9": "I-LOC",
"10": "I-PER",
"11": "I-ORG",
"12": "O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-FAC": 8,
"B-GPE": 0,
"B-LOC": 1,
"B-ORG": 2,
"B-PER": 4,
"B-VEH": 3,
"I-FAC": 5,
"I-GPE": 7,
"I-LOC": 9,
"I-ORG": 11,
"I-PER": 10,
"I-VEH": 6,
"O": 12
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.25.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}