| { | |
| "_name_or_path": "xlnet-large-cased", | |
| "architectures": [ | |
| "XLNetForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "attn_type": "bi", | |
| "bi_data": false, | |
| "bos_token_id": 1, | |
| "clamp_len": -1, | |
| "classifier_dropout": 0.1, | |
| "d_head": 64, | |
| "d_inner": 4096, | |
| "d_model": 1024, | |
| "dropout": 0.1, | |
| "end_n_top": 5, | |
| "eos_token_id": 2, | |
| "ff_activation": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-12, | |
| "mem_len": null, | |
| "model_type": "xlnet", | |
| "n_head": 16, | |
| "n_layer": 24, | |
| "pad_token_id": 5, | |
| "problem_type": "single_label_classification", | |
| "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 | |
| } | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.31.0", | |
| "untie_r": true, | |
| "use_mems_eval": true, | |
| "use_mems_train": false, | |
| "vocab_size": 32000 | |
| } | |