albert/albert-large-v2

1{2  "architectures": [3    "AlbertForMaskedLM"4  ],5  "attention_probs_dropout_prob": 0,6  "bos_token_id": 2,7  "classifier_dropout_prob": 0.1,8  "down_scale_factor": 1,9  "embedding_size": 128,10  "eos_token_id": 3,11  "gap_size": 0,12  "hidden_act": "gelu_new",13  "hidden_dropout_prob": 0,14  "hidden_size": 1024,15  "initializer_range": 0.02,16  "inner_group_num": 1,17  "intermediate_size": 4096,18  "layer_norm_eps": 1e-12,19  "max_position_embeddings": 512,20  "model_type": "albert",21  "net_structure_type": 0,22  "num_attention_heads": 16,23  "num_hidden_groups": 1,24  "num_hidden_layers": 24,25  "num_memory_blocks": 0,26  "pad_token_id": 0,27  "type_vocab_size": 2,28  "vocab_size": 3000029}30