| { |
| "backend": "tokenizers", |
| "bos_token": "<s>", |
| "cls_token": "<s>", |
| "eos_token": "</s>", |
| "extra_special_tokens": [ |
| "<s_iitcdip>", |
| "<s_synthdog>" |
| ], |
| "from_slow": true, |
| "is_local": true, |
| "mask_token": "<mask>", |
| "max_length": 256, |
| "model_max_length": 1000000000000000019884624838656, |
| "pad_to_multiple_of": null, |
| "pad_token": "<pad>", |
| "pad_token_type_id": 0, |
| "padding_side": "right", |
| "processor_class": "DonutProcessor", |
| "sep_token": "</s>", |
| "sp_model_kwargs": {}, |
| "stride": 0, |
| "tokenizer_class": "TokenizersBackend", |
| "truncation_side": "right", |
| "truncation_strategy": "longest_first", |
| "unk_token": "<unk>" |
| } |
|
|