{
  "_name_or_path": "albert",
  "architectures": [
    "AlbertForPreTraining"
  ],
  "attention_probs_dropout_prob": 0,
  "bos_token_id": 2,
  "classifier_dropout_prob": 0.1,
  "embedding_size": 128,
  "eos_token_id": 3,
  "hidden_act": "relu",
  "hidden_dropout_prob": 0,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "inner_group_num": 1,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "albert",
  "num_attention_heads": 12,
  "num_hidden_groups": 1,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "tie_word_embeddings": 0,
  "transformers_version": "4.6.0",
  "type_vocab_size": 2,
  "vocab_size": 21128
}