{
    "model_type": "gpt2",
    "architectures": ["GPT2LMHeadModel"],
    "attention_probs_dropout_prob": 0.1,
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "max_position_embeddings": 1024,
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "vocab_size": 50257
}