config.json

{
  "architectures": [
    "MyBertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_mybert.MyBertConfig",
    "AutoModelForMaskedLM": "modeling_mybert.MyBertForMaskedLM",
    "AutoModel": "modeling_mybert.MyBertModel"
  },
  "dtype": "float32",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 128,
  "model_type": "mybert",
  "num_attention_heads": 8,
  "num_hidden_layers": 8,
  "pad_token_id": 0,
  "rope_theta": 10000.0,
  "tie_word_embeddings": true,
  "transformers_version": "5.0.0",
  "vocab_size": 16839
}