config.json

{
  "architectures": [
    "DualBertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "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": 256,
  "model_type": "dual_bert",
  "num_attention_heads": 8,
  "num_hidden_layers": 6,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.48.0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_char_size": 156,
  "vocab_size": 156,
  "vocab_word_size": 50000,
  "word_char_emb_dim": 192,
  "auto_map": {
    "AutoConfig": "configuration_dual.DualBertConfig",
    "AutoModelForMaskedLM": "modeling_dual.DualBertForMaskedLM"
  }
}