{
  "_name_or_path": "models/fleonce/iter-conll03-deberta-large",
  "activation_fn": "relu",
  "architectures": [
    "ITER"
  ],
  "d_ff": 1500,
  "d_model": 1024,
  "dataset": "conll03",
  "dropout": 0.3,
  "entity_types": [
    "ORG",
    "LOC",
    "MISC",
    "PER"
  ],
  "features": 2099200,
  "link_types": [],
  "max_length": 4096,
  "max_nest_depth": 1,
  "model_type": "iter",
  "num_links": 0,
  "num_types": 4,
  "threshold": 0.5,
  "torch_dtype": "float32",
  "transformer_config": {
    "_name_or_path": "microsoft/deberta-v3-large",
    "architectures": null,
    "attention_probs_dropout_prob": 0.1,
    "decoder_start_token_id": null,
    "eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_encoder_decoder": false,
    "layer_norm_eps": 1e-07,
    "max_length": 4096,
    "max_position_embeddings": 512,
    "max_relative_positions": -1,
    "model_type": "deberta-v2",
    "norm_rel_ebd": "layer_norm",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "pooler_dropout": 0,
    "pooler_hidden_act": "gelu",
    "pooler_hidden_size": 1024,
    "pos_att_type": [
      "p2c",
      "c2p"
    ],
    "position_biased_input": false,
    "position_buckets": 256,
    "relative_attention": true,
    "share_att_key": true,
    "task_specific_params": null,
    "type_vocab_size": 0,
    "vocab_size": 128100
  },
  "transformers_version": "4.37.0",
  "use_bias": false,
  "use_gate": true,
  "use_mlp": true,
  "use_scale": false
}