{
  "add_cross_attention": false,
  "architectures": [
    "XLMRobertaForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "custom_head": "entity_start_marker_meanmask (concat E1,E2 -> Linear); [CLS] is not read",
  "dtype": "float32",
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 384,
  "id2label": {
    "0": "NO_RELATION",
    "1": "semantically_similar_to",
    "2": "supersedes_or_conflicts",
    "3": "depends_on"
  },
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "is_decoder": false,
  "label2id": {
    "NO_RELATION": 0,
    "semantically_similar_to": 1,
    "supersedes_or_conflicts": 2,
    "depends_on": 3
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "xlm-roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "num_labels": 4,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
  "tie_word_embeddings": true,
  "transformers_version": "5.1.0",
  "type_vocab_size": 1,
  "ultracode_note": "Inference artefact is model.onnx (inputs: input_ids, attention_mask; output: logits[batch, 4]). Feed the pair as (empty query, marked passage).",
  "use_cache": true,
  "vocab_size": 250006,
  "ultracode": {
    "format": "raw-safetensors/1",
    "exported_from": "model.onnx",
    "onnx_sha256": "9189bfedd376d2a08acd18e7b490000d5f78458c3e4388d1089704319a115840",
    "head": "entity_pool",
    "position_ids": "roberta",
    "pooling": "mean of the last hidden state over the tokens equal to each marker id; concat(E1, E2) -> classifier",
    "entity_marker_ids": [
      250002,
      250004
    ]
  }
}