cooelf/Retro-Reader

1{2  "attention_probs_dropout_prob": 0,3  "hidden_act": "gelu",4  "hidden_dropout_prob": 0,5  "embedding_size": 128,6  "hidden_size": 4096,7  "initializer_range": 0.02,8  "intermediate_size": 16384,9  "max_position_embeddings": 512,10  "num_attention_heads": 64,11  "num_hidden_layers": 12,12  "num_hidden_groups": 1,13  "net_structure_type": 0,14  "layers_to_keep": [],15  "gap_size": 0,16  "num_memory_blocks": 0,17  "inner_group_num": 1,18  "down_scale_factor": 1,19  "type_vocab_size": 2,20  "vocab_size": 3000021}