config.json

{
  "architectures": [
    "CaduceusForMaskedLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_caduceus.CaduceusConfig",
    "AutoModel": "modeling_caduceus.Caduceus",
    "AutoModelForMaskedLM": "modeling_caduceus.CaduceusForMaskedLM",
    "AutoModelForSequenceClassification": "modeling_caduceus.CaduceusForSequenceClassification"
  },
  "bidirectional": true,
  "bidirectional_strategy": "add",
  "bidirectional_weight_tie": true,
  "complement_map": {
    "0": 0,
    "1": 1,
    "2": 2,
    "3": 3,
    "4": 4,
    "5": 5,
    "6": 6,
    "7": 10,
    "8": 9,
    "9": 8,
    "10": 7,
    "11": 11,
    "12": 12,
    "13": 13,
    "14": 14,
    "15": 15
  },
  "d_model": 118,
  "fused_add_norm": true,
  "initializer_cfg": {
    "initializer_range": 0.02,
    "n_residuals_per_layer": 1,
    "rescale_prenorm_residual": true
  },
  "model_type": "caduceus",
  "n_layer": 4,
  "norm_epsilon": 1e-05,
  "pad_vocab_size_multiple": 8,
  "rcps": true,
  "residual_in_fp32": false,
  "rms_norm": true,
  "ssm_cfg": {
    "bias": false,
    "conv_bias": true,
    "d_conv": 4,
    "d_state": 16,
    "dt_init": "random",
    "dt_init_floor": 0.0001,
    "dt_max": 0.1,
    "dt_min": 0.001,
    "dt_rank": "auto",
    "dt_scale": 1.0,
    "expand": 2,
    "use_fast_path": true
  },
  "torch_dtype": "float32",
  "transformers_version": "4.38.1",
  "vocab_size": 16
}