train/models/bert/xlarge_config.json

{
  "emb_size": 1536,
  "feedforward_size": 6144,
  "hidden_size": 1536,
  "hidden_act": "gelu",
  "heads_num": 24,
  "layers_num": 36,
  "max_seq_length": 512,
  "dropout": 0.1,
  "data_processor": "bert",
  "embedding": ["word", "pos", "seg"],
  "encoder": "transformer",
  "mask": "fully_visible",
  "target": ["mlm", "sp"],
  "tie_weights": true
}