{ "attn_type": "bi", "bi_data": false, "clamp_len": -1, "d_head": 64, "d_inner": 4096, "d_model": 1024, "dropatt": 0.1, "dropout": 0.1, "ff_activation": "gelu", "init": "normal", "init_range": 0.1, "init_std": 0.02, "initializer_range": 0.02, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "mem_len": null, "n_head": 16, "n_layer": 24, "n_token": 32000, "reuse_len": null, "same_length": false, "untie_r": true }