ner-DarijaBERT-arabizi / config.json
Oelbourki's picture
Training in progress, epoch 1
a27931a verified
raw
history blame
1.19 kB
{
"_name_or_path": "SI2M-Lab/DarijaBERT-arabizi",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"cls_token": "[CLS]",
"do_lower_case": true,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "I-PER",
"2": "I-ORG",
"3": "I-MISC",
"4": "I-LOC",
"5": "B-PER",
"6": "B-ORG",
"7": "B-MISC",
"8": "B-LOC"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-LOC": 8,
"B-MISC": 7,
"B-ORG": 6,
"B-PER": 5,
"I-LOC": 4,
"I-MISC": 3,
"I-ORG": 2,
"I-PER": 1,
"O": 0
},
"layer_norm_eps": 1e-12,
"mask_token": "[MASK]",
"max_len": 128,
"max_position_embeddings": 512,
"model_max_length": 128,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token": "[PAD]",
"pad_token_id": 0,
"position_embedding_type": "absolute",
"sep_token": "[SEP]",
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"type_vocab_size": 2,
"unk_token": "[UNK]",
"use_cache": true,
"vocab_size": 110000
}