{
  "_name_or_path": "roberta-large",
  "architectures": [
    "RobertaForSequenceClassification"
  ],
  "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": "Paraphrase",
    "1": "Subsumption",
    "2": "Overlap",
    "3": "Sub-reference",
    "4": "Reader profile",
    "5": "Contradiction",
    "6": "Change of perspective",
    "7": "Historical background",
    "8": "Fulfillment",
    "9": "Cross-reference",
    "10": "Citation",
    "11": "Attribution",
    "12": "Indirect speech",
    "13": "Elaboration",
    "14": "Follow up",
    "15": "Summary",
    "16": "Generalization",
    "17": "Modality"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_10": 10,
    "LABEL_11": 11,
    "LABEL_12": 12,
    "LABEL_13": 13,
    "LABEL_14": 14,
    "LABEL_15": 15,
    "LABEL_16": 16,
    "LABEL_17": 17,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7,
    "LABEL_8": 8,
    "LABEL_9": 9
  },
  "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",
  "torch_dtype": "float32",
  "transformers_version": "4.35.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 50265
}