config.json

{
  "architectures": [
    "HATForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "encoder_layout": {
    "0": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "1": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "10": {
      "document_encoder": false,
      "sentence_encoder": true
    },
    "11": {
      "document_encoder": true,
      "sentence_encoder": true
    },
    "2": {
      "document_encoder": true,
      "sentence_encoder": true
    },
    "3": {
      "document_encoder": false,
      "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": false,
      "sentence_encoder": true
    },
    "8": {
      "document_encoder": true,
      "sentence_encoder": true
    },
    "9": {
      "document_encoder": false,
      "sentence_encoder": true
    }
  },
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 128,
  "max_sentence_length": 128,
  "max_sentences": 32,
  "model_max_length": 4096,
  "model_type": "hat",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "sentence_split_strategy": "standrad",
  "torch_dtype": "float32",
  "transformers_version": "4.24.0.dev0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 50265
}