NusaBert-ner / config.json
cahya's picture
Training in progress, epoch 1
858aa1b verified
{
"_name_or_path": "cahya/NusaBert-v0.5",
"architectures": [
"ModernBertForTokenClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 65003,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "cls",
"cls_token_id": 65003,
"decoder_bias": true,
"deterministic_flash_attn": false,
"embedding_dropout": 0.0,
"eos_token_id": 65001,
"global_attn_every_n_layers": 3,
"global_rope_theta": 160000.0,
"hidden_activation": "gelu",
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-PER",
"2": "I-PER",
"3": "B-ORG",
"4": "I-ORG",
"5": "B-LOC",
"6": "I-LOC",
"7": "B-MISC",
"8": "I-MISC"
},
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 1152,
"label2id": {
"B-LOC": 5,
"B-MISC": 7,
"B-ORG": 3,
"B-PER": 1,
"I-LOC": 6,
"I-MISC": 8,
"I-ORG": 4,
"I-PER": 2,
"O": 0
},
"local_attention": 128,
"local_rope_theta": 10000.0,
"max_position_embeddings": 8192,
"mlp_bias": false,
"mlp_dropout": 0.0,
"model_type": "modernbert",
"norm_bias": false,
"norm_eps": 1e-05,
"num_attention_heads": 12,
"num_hidden_layers": 22,
"pad_token_id": 65002,
"reference_compile": false,
"repad_logits_with_grad": false,
"sep_token_id": 65001,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"torch_dtype": "float32",
"transformers_version": "4.48.2",
"vocab_size": 65107
}