config.json

{
    "architectures": [
          "GPTBERTFoCausalLM"
      ],
      "auto_map": {
          "AutoConfig": "configuration_gpt_bert.ModelConfig",
          "AutoModel": "modeling_gpt_bert.GPTBERT",
          "AutoModelForCausalLM": "modeling_gpt_bert.GPTBERTForCausalLM",
          "AutoModelForMaskedLM": "modeling_gpt_bert.GPTBERTForMaskedLM"
      },
    "attention_probs_dropout_prob": 0.1,
    "hidden_dropout_prob": 0.1,
    "hidden_size": 384,
    "intermediate_size": 1280,
    "max_position_embeddings": 512,
    "position_bucket_size": 32,
    "num_attention_heads": 6,
    "num_hidden_layers": 12,
    "vocab_size": 4096,
    "layer_norm_eps": 1.0e-5
  }