order_benchmark_xlnet / config.json
system's picture
system
HF staff
Update config.json 3bdf8f6
{
"architectures": [
"XLNetForMultipleChoice"
],
"attn_type": "bi",
"bi_data": false,
"bos_token_id": 1,
"clamp_len": -1,
"d_head": 64,
"d_inner": 3072,
"d_model": 768,
"do_sample": false,
"dropout": 0.1,
"end_n_top": 5,
"eos_token_id": 2,
"eos_token_ids": 0,
"ff_activation": "gelu",
"finetuning_task": "swag",
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"mem_len": null,
"model_type": "xlnet",
"n_head": 12,
"n_layer": 12,
"num_beams": 1,
"num_labels": 4,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_past": true,
"pad_token_id": 5,
"pruned_heads": {},
"repetition_penalty": 1.0,
"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
}
},
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"untie_r": true,
"use_bfloat16": false,
"vocab_size": 32000
}