| { | |
| "attn_type": "bi", | |
| "bi_data": false, | |
| "clamp_len": -1, | |
| "d_head": 64, | |
| "d_inner": 3072, | |
| "d_model": 768, | |
| "dropout": 0.1, | |
| "end_n_top": 5, | |
| "ff_activation": "relu", | |
| "finetuning_task": null, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-12, | |
| "mem_len": null, | |
| "n_head": 12, | |
| "n_layer": 12, | |
| "n_token": 32000, | |
| "num_labels": 2, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "reuse_len": null, | |
| "same_length": false, | |
| "start_n_top": 5, | |
| "summary_activation": "tanh", | |
| "summary_last_dropout": 0.1, | |
| "summary_type": "last", | |
| "summary_use_proj": true, | |
| "torchscript": false, | |
| "untie_r": true | |
| } | |