lang-detection / config.json
blancsw's picture
Upload XLMRobertaForSequenceClassification
c3aa675 verified
{
"_name_or_path": "papluca/xlm-roberta-base-language-detection",
"architectures": [
"XLMRobertaForSequenceClassification"
],
"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": "ja",
"1": "nl",
"2": "ar",
"3": "pl",
"4": "de",
"5": "it",
"6": "pt",
"7": "tr",
"8": "es",
"9": "hi",
"10": "el",
"11": "ur",
"12": "bg",
"13": "en",
"14": "fr",
"15": "zh",
"16": "ru",
"17": "th",
"18": "sw",
"19": "vi"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"ar": 2,
"bg": 12,
"de": 4,
"el": 10,
"en": 13,
"es": 8,
"fr": 14,
"hi": 9,
"it": 5,
"ja": 0,
"nl": 1,
"pl": 3,
"pt": 6,
"ru": 16,
"sw": 18,
"th": 17,
"tr": 7,
"ur": 11,
"vi": 19,
"zh": 15
},
"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",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.37.2",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}