{
  "_name_or_path": "xlm-roberta-large",
  "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": 1024,
  "id2label": {
    "0": "nso",
    "1": "tsn",
    "10": "eng",
    "2": "sot",
    "3": "ven",
    "4": "af",
    "5": "tso",
    "6": "ssw",
    "7": "zul",
    "8": "xho",
    "9": "nbl"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "af": 4,
    "eng": 10,
    "nbl": 9,
    "nso": 0,
    "sot": 2,
    "ssw": 6,
    "tsn": 1,
    "tso": 5,
    "ven": 3,
    "xho": 8,
    "zul": 7
  },
  "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",
  "problem_type": "single_label_classification",
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 250002
}