xddModel / config.json
pushokay's picture
End of training
af86088 verified
{
"_name_or_path": "ukr-models/xlm-roberta-base-uk",
"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": 768,
"id2label": {
"0": "o",
"1": "geo_region",
"2": "geo_city",
"3": "geo_district",
"4": "central_city",
"5": "geo_street",
"6": "geo_address",
"7": "geo_building",
"8": "geo_region_oblast",
"9": "geo_microdistrict"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"central_city": 4,
"geo_address": 6,
"geo_building": 7,
"geo_city": 2,
"geo_district": 3,
"geo_microdistrict": 9,
"geo_region": 1,
"geo_region_oblast": 8,
"geo_street": 5,
"o": 0
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 31274
}