{
  "architectures": [
    "GPTBertForCausalLM",
    "GPTBertForMaskedLM",
    "LtgbertFoCausalLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_gpt_bert.GPTBertConfig",
    "AutoModel": "modeling_gpt_bert.GPTBertForCausalLM",
    "AutoModelForCausalLM": "modeling_gpt_bert.GPTBertForCausalLM",
    "AutoModelForMaskedLM": "modeling_gpt_bert.GPTBertForMaskedLM"
  },
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 512,
  "model_type": "gpt_bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "position_bucket_size": 32,
  "temperature": 2.65,
  "torch_dtype": "float32",
  "vocab_size": 32768
}