config.json

{
  "architectures": [
    "UnifiedTransformerLMHeadModel"
  ],
  "vocab_size": 30001,
  "hidden_size": 768,
  "num_hidden_layers": 6,
  "num_attention_heads": 12,
  "intermediate_size": 3072,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "attention_probs_dropout_prob": 0.1,
  "normalize_before": true,
  "max_position_embeddings": 512,
  "type_vocab_size": 2,
  "initializer_range": 0.02,
  "unk_token_id": 0,
  "pad_token_id": 0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "mask_token_id": 30000
}