{
  "_name_or_path": "ai-forever/ruRoberta-large",
  "architectures": [
    "RobertaForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 1,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "id2label": {
    "0": "\u0444\u0438\u043b\u044c\u0442\u0440",
    "1": "\u0432\u0441\u043f\u043e\u043c\u043e\u0433\u0430\u0442\u0435\u043b\u044c\u043d\u0430\u044f \u0434\u0435\u0442\u0430\u043b\u044c \u0434\u043b\u044f \u0444\u0438\u043b\u044c\u0442\u0440\u0430",
    "2": "\u0434\u0440\u0443\u0433\u0430\u044f \u0434\u0435\u0442\u0430\u043b\u044c",
    "3": "\u0434\u0440\u0443\u0433\u043e\u0439 \u0432\u0438\u0434 \u0444\u0438\u043b\u044c\u0442\u0440\u0430",
    "4": "\u043d\u0430\u0431\u043e\u0440 \u0434\u0435\u0442\u0430\u043b\u0435\u0439"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "\u0432\u0441\u043f\u043e\u043c\u043e\u0433\u0430\u0442\u0435\u043b\u044c\u043d\u0430\u044f \u0434\u0435\u0442\u0430\u043b\u044c \u0434\u043b\u044f \u0444\u0438\u043b\u044c\u0442\u0440\u0430": 1,
    "\u0434\u0440\u0443\u0433\u0430\u044f \u0434\u0435\u0442\u0430\u043b\u044c": 2,
    "\u0434\u0440\u0443\u0433\u043e\u0439 \u0432\u0438\u0434 \u0444\u0438\u043b\u044c\u0442\u0440\u0430": 3,
    "\u043d\u0430\u0431\u043e\u0440 \u0434\u0435\u0442\u0430\u043b\u0435\u0439": 4,
    "\u0444\u0438\u043b\u044c\u0442\u0440": 0
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "problem_type": "single_label_classification",
  "torch_dtype": "float32",
  "transformers_version": "4.42.4",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 50265
}