mbert-ner-baseline-1 / config.json
imtiaz114's picture
Training in progress epoch 0
48b938f
{
"_name_or_path": "sagorsarker/mbert-bengali-ner",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "B-ORG",
"1": "I-LOC",
"2": "B-PER",
"3": "I-PER",
"4": "O",
"5": "I-ORG",
"6": "B-LOC"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-LOC": 6,
"B-ORG": 0,
"B-PER": 2,
"I-LOC": 1,
"I-ORG": 5,
"I-PER": 3,
"O": 4
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"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",
"transformers_version": "4.31.0.dev0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 105879
}