ewc_stabilised / config.json
Mardiyyah's picture
Mlr-shared-task-ewc_stabilised
5af906c verified
{
"_name_or_path": "masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0",
"adapters": {
"adapters": {},
"config_map": {},
"fusion_config_map": {},
"fusions": {}
},
"architectures": [
"XLMRobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "O",
"1": "B-DATE",
"2": "I-DATE",
"3": "B-PER",
"4": "I-PER",
"5": "B-ORG",
"6": "I-ORG",
"7": "B-LOC",
"8": "I-LOC"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"B-DATE": 1,
"B-LOC": 7,
"B-ORG": 5,
"B-PER": 3,
"I-DATE": 2,
"I-LOC": 8,
"I-ORG": 6,
"I-PER": 4,
"O": 0
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.43.4",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}