{
  "_name_or_path": "data/PLMs/hat-p2_1-grouped",
  "architectures": [
    "HATForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_hat.HATConfig",
    "AutoModel": "modelling_hat.HATModel",
    "AutoModelForMaskedLM": "modelling_hat.HATForMaskedLM",
    "AutoModelForSequenceClassification": "modelling_hat.HATForSequenceClassification"
  },
  "classifier_dropout": null,
  "encoder_layout": {
    "0": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "1": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "2": {
      "document_encoder": true,
      "sentence_encoder": true
    }
  },
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 264,
  "initializer_range": 0.02,
  "intermediate_size": 792,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 128,
  "max_sentence_length": 128,
  "max_sentence_size": 128,
  "max_sentences": 4,
  "model_max_length": 512,
  "model_type": "hierarchical-transformer",
  "num_attention_heads": 12,
  "num_hidden_layers": 3,
  "output_past": true,
  "pad_token_id": 0,
  "parameters": 136350720,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.42.4",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 30522
}