| { | |
| "additional_special_tokens": [ | |
| "<special0>", | |
| "<special1>", | |
| "<special2>", | |
| "<special3>", | |
| "<special4>", | |
| "<special5>", | |
| "<special6>", | |
| "<special7>", | |
| "<special8>", | |
| "<special9>" | |
| ], | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "</s>", | |
| "do_lower_case": false, | |
| "id2lang": null, | |
| "keep_accents": true, | |
| "lang2id": null, | |
| "mask_token": "<special1>", | |
| "model_max_length": 512, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "tokenizer_class": "FlaubertTokenizer", | |
| "tokenizer_file": null, | |
| "unk_token": "<unk>" | |
| } | |