hindi-muril-ner / config.json
mirfan899's picture
End of training
b7b13f5
raw
history blame
1.35 kB
{
"_name_or_path": "bert-base-multilingual-cased",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LOCATION",
"1": "BRAND",
"2": "TITLE_OBJECT",
"3": "PERSON",
"4": "DESIGNATION",
"5": "ORGANIZATION",
"6": "ABBREVIATION",
"7": "TIME",
"8": "NUMBER",
"9": "MEASURE",
"10": "TERMS",
"11": "O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"ABBREVIATION": 6,
"BRAND": 1,
"DESIGNATION": 4,
"LOCATION": 0,
"MEASURE": 9,
"NUMBER": 8,
"O": 11,
"ORGANIZATION": 5,
"PERSON": 3,
"TERMS": 10,
"TIME": 7,
"TITLE_OBJECT": 2
},
"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",
"torch_dtype": "float32",
"transformers_version": "4.33.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}