{
  "_name_or_path": "../experiments_final/model_dbmdz_bert_medium_historic_multilingual_cased_max_sequence_length_512_epochs_5_run_extended_suffix_baseline/checkpoint-450",
  "architectures": [
    "ExtendedMultitaskModelForTokenClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "custom_pipelines": {
    "generic-ner": {
      "impl": "generic_ner.MultitaskTokenClassificationPipeline",
      "pt": "models.ExtendedMultitaskModelForTokenClassification",
      "tf": []
    }
  },
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 8,
  "num_hidden_layers": 8,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.40.0.dev0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 32000
}