38 lines
760 B
JSON
38 lines
760 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"XLNetLMHeadModel"
|
||
|
|
],
|
||
|
|
"attn_type": "bi",
|
||
|
|
"bi_data": false,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"clamp_len": -1,
|
||
|
|
"d_head": 64,
|
||
|
|
"d_inner": 3072,
|
||
|
|
"d_model": 768,
|
||
|
|
"dropout": 0.1,
|
||
|
|
"end_n_top": 5,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"ff_activation": "gelu",
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"layer_norm_eps": 1e-12,
|
||
|
|
"mem_len": null,
|
||
|
|
"model_type": "xlnet",
|
||
|
|
"n_head": 12,
|
||
|
|
"n_layer": 12,
|
||
|
|
"pad_token_id": 5,
|
||
|
|
"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,
|
||
|
|
"task_specific_params": {
|
||
|
|
"text-generation": {
|
||
|
|
"do_sample": true,
|
||
|
|
"max_length": 250
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"untie_r": true,
|
||
|
|
"vocab_size": 32000
|
||
|
|
}
|