| { |
| "added_tokens_decoder": { |
| "0": { |
| "content": "<CLS>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "1": { |
| "content": "<SEP>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "2": { |
| "content": "<UNK>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "3": { |
| "content": "<PAD>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "4": { |
| "content": "<MASK>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "auto_map": { |
| "AutoTokenizer": [ |
| "tokenization_encodon.EnCodonTokenizer", |
| null |
| ] |
| }, |
| "bos_token": "<CLS>", |
| "clean_up_tokenization_spaces": true, |
| "cls_token": "<CLS>", |
| "mask_token": "<MASK>", |
| "model_max_length": 2048, |
| "pad_token": "<PAD>", |
| "sep_token": "<SEP>", |
| "tokenizer_class": "EnCodonTokenizer", |
| "unk_token": "<UNK>" |
| } |
|
|
