bert_sesame_ner / config.json
ricardo-filho's picture
Training in progress, step 500
c06ab61
raw
history blame
1.51 kB
{
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"finetuning_task": "ner",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "B-LOC-ANOT",
"1": "B-LOC-PRED",
"2": "B-ORG-ANOT",
"3": "B-ORG-PRED",
"4": "B-PER-ANOT",
"5": "B-PER-PRED",
"6": "I-LOC-ANOT",
"7": "I-LOC-PRED",
"8": "I-ORG-ANOT",
"9": "I-ORG-PRED",
"10": "I-PER-ANOT",
"11": "I-PER-PRED",
"12": "O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-LOC-ANOT": 0,
"B-LOC-PRED": 1,
"B-ORG-ANOT": 2,
"B-ORG-PRED": 3,
"B-PER-ANOT": 4,
"B-PER-PRED": 5,
"I-LOC-ANOT": 6,
"I-LOC-PRED": 7,
"I-ORG-ANOT": 8,
"I-ORG-PRED": 9,
"I-PER-ANOT": 10,
"I-PER-PRED": 11,
"O": 12
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"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": "4.25.0.dev0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 29794
}