{
  "architectures": [
    "CustomBERTModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert-refine",
  "num_attention_heads": 8,
  "num_hidden_layers": 8,
  "post_batch_size": 32,
  "refine_layer_size": 8,
  "torch_dtype": "float32",
  "transformers_version": "4.38.0.dev0",
  "type_vocab_size": 2,
  "vocab_size": 30522
}