{
  "architectures": [
    "UltrabertModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_windows": [
    128,
    128,
    null,
    128,
    128,
    null,
    128,
    128,
    null,
    128,
    128,
    null,
    128,
    128,
    null,
    128,
    128,
    null,
    128,
    128,
    null,
    128,
    128,
    null
  ],
  "auto_map": {
    "AutoConfig": "configuration_ultrabert.UltrabertConfig",
    "AutoModel": "modeling_ultrabert.UltrabertModel",
    "AutoModelForMaskedLM": "modeling_ultrabert.UltrabertForMaskedLM",
    "AutoModelForSequenceClassification": "modeling_ultrabert.UltrabertForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_ultrabert.UltrabertForTokenClassification",
    "AutoModelForQuestionAnswering": "modeling_ultrabert.UltrabertForQuestionAnswering"
  },
  "bos_token_id": 0,
  "classifier_dropout": 0.0,
  "dtype": "float32",
  "eos_token_id": 0,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "mlp_bias": false,
  "model_type": "ultrabert",
  "num_attention_heads": 8,
  "num_hidden_layers": 24,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "prediction_head_size": 1024,
  "rms_norm_eps": 1e-06,
  "rope_theta": [
    10000.0,
    10000.0,
    2560000.0,
    10000.0,
    10000.0,
    2560000.0,
    10000.0,
    10000.0,
    2560000.0,
    10000.0,
    10000.0,
    2560000.0,
    10000.0,
    10000.0,
    2560000.0,
    10000.0,
    10000.0,
    2560000.0,
    10000.0,
    10000.0,
    2560000.0,
    10000.0,
    10000.0,
    2560000.0
  ],
  "tie_word_embeddings": false,
  "transformers_version": "5.16.1",
  "vocab_size": 49160,
  "decision": {
    "model": "vela3-fast decision backbone (soup_X2)",
    "marker_ids": {
      "[Q]": 49152,
      "[O]": 49153,
      "[ABS]": 49154,
      "[SEP_SCHEMA]": 49155,
      "[SEG_user]": 49156,
      "[SEG_answer]": 49157,
      "[E]": 49158,
      "[SEG_context]": 49159
    },
    "n_vocab": 49160,
    "n_vocab_base": 49152,
    "proj_dim": 256,
    "readout": "both (cosine/tau + MLP at the [O] markers)",
    "tau": 0.0635916069149971,
    "max_len": 32768,
    "rendering": "ub_d3_common.to_row",
    "noul": "2-option choice {no, yes}; answer = p(yes)"
  }
}