ner_roberta_model / config.json
pritmanvar's picture
End of training
4c71718 verified
{
"_name_or_path": "xlm-roberta-large",
"architectures": [
"XLMRobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "O",
"1": "B-ORG",
"2": "I-ORG",
"3": "B-GCNUMBER",
"4": "I-GCNUMBER",
"5": "B-BGNUMBER",
"6": "I-BGNUMBER",
"7": "B-NAME",
"8": "I-NAME",
"9": "B-LOCATION",
"10": "I-LOCATION",
"11": "B-COUNTRY",
"12": "I-COUNTRY"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"B-BGNUMBER": 5,
"B-COUNTRY": 11,
"B-GCNUMBER": 3,
"B-LOCATION": 9,
"B-NAME": 7,
"B-ORG": 1,
"I-BGNUMBER": 6,
"I-COUNTRY": 12,
"I-GCNUMBER": 4,
"I-LOCATION": 10,
"I-NAME": 8,
"I-ORG": 2,
"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": "4.39.1",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}