{
  "_name_or_path": "/content/hierarchical-transformers/data/PLMs/hi-transformer-p1-grouped/",
  "architectures": [
    "HATForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "encoder_layout": {
    "0": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "1": {
      "document_encoder": true,
      "sentence_encoder": true
    },
    "2": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "3": {
      "document_encoder": true,
      "sentence_encoder": true
    },
    "4": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "5": {
      "document_encoder": true,
      "sentence_encoder": true
    },
    "6": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "7": {
      "document_encoder": true,
      "sentence_encoder": true
    }
  },
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 256,
  "initializer_range": 0.02,
  "intermediate_size": 1024,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 128,
  "max_sentence_length": 128,
  "max_sentence_size": 128,
  "max_sentences": 5,
  "model_max_length": 640,
  "model_type": "hi-transformer",
  "num_attention_heads": 4,
  "num_hidden_layers": 8,
  "output_past": true,
  "pad_token_id": 0,
  "parameters": 136350720,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.29.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 30522
}