| { |
| "tokenizer_class": "PreTrainedTokenizerFast", |
| "model_max_length": 128, |
| "bos_token": "<S>", |
| "eos_token": "<E>", |
| "unk_token": "<unk>", |
| "pad_token": "<pad>", |
| "mask_token": "<mask>", |
| "additional_special_tokens": [ |
| "<U>", |
| "<A>", |
| "<Y>", |
| "<C>", |
| "<H>" |
| ], |
| "bos_token_id": 0, |
| "eos_token_id": 2, |
| "unk_token_id": 9, |
| "pad_token_id": 7, |
| "mask_token_id": 8, |
| "clean_up_tokenization_spaces": false, |
| "model_type_internal": "BPE", |
| "decoder": "ByteLevel", |
| "pre_tokenizer": "ByteLevel", |
| "normalizer": null, |
| "has_post_processor": true |
| } |
|
|
