multibertfinetuned1107 / config.json
Tommert25's picture
Training in progress, epoch 1
829045d
raw
history blame
1.26 kB
{
"_name_or_path": "bert-base-multilingual-uncased",
"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": "Name",
"1": "Other (OTH)",
"2": "Dutch (NL)",
"3": "VAR",
"4": "Arabic (ARAB)",
"5": "English (EN)",
"6": "Borrow (BOR)",
"7": "Mixed",
"8": "Straattaal"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"Arabic (ARAB)": 4,
"Borrow (BOR)": 6,
"Dutch (NL)": 2,
"English (EN)": 5,
"Mixed": 7,
"Name": 0,
"Other (OTH)": 1,
"Straattaal": 8,
"VAR": 3
},
"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": "4.31.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 105879
}