| { |
| "added_tokens_decoder": { |
| "42037": { |
| "content": "[CLS]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "42038": { |
| "content": "[SEP]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "42039": { |
| "content": "[UNK]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "42040": { |
| "content": "[PAD]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "42041": { |
| "content": "[MASK]", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "auto_map": { |
| "AutoTokenizer": [ |
| "tokenizer.GreekSyllableTokenizer", |
| null |
| ] |
| }, |
| "bos_token": "[CLS]", |
| "clean_up_tokenization_spaces": false, |
| "cls_token": "[CLS]", |
| "eos_token": "[SEP]", |
| "extra_special_tokens": {}, |
| "mask_token": "[MASK]", |
| "model_max_length": 514, |
| "pad_token": "[PAD]", |
| "sep_token": "[SEP]", |
| "tokenizer_class": "GreekSyllableTokenizer", |
| "unk_token": "[UNK]" |
| } |
|
|
