train/models/albert/xlarge_config.json

{
  "emb_size": 128,
  "feedforward_size": 8192,
  "hidden_size": 2048,
  "hidden_act": "relu",
  "heads_num": 16,
  "layers_num": 24,
  "max_seq_length": 512,
  "dropout": 0.0,
  "data_processor": "albert",
  "embedding": ["word", "pos", "seg"],
  "encoder": "transformer",
  "mask": "fully_visible",
  "factorized_embedding_parameterization": true,
  "parameter_sharing": true,
  "target": ["mlm", "sp"]
}