| { |
| "added_tokens_decoder": { |
| "0": { |
| "content": "UNK", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "1": { |
| "content": "CLS", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "2": { |
| "content": "SEP", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "3": { |
| "content": "PAD", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "4": { |
| "content": "MASK", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "bos_token": "CLS", |
| "chat_template": "{% for message in messages %}{{ message['content'] }}{% endfor %}", |
| "clean_up_tokenization_spaces": false, |
| "cls_token": "CLS", |
| "eos_token": "SEP", |
| "mask_token": "MASK", |
| "max_new_tokens": 1048576, |
| "model_max_length": 1048576, |
| "pad_token": "PAD", |
| "padding_side": "right", |
| "sep_token": "SEP", |
| "tokenizer_class": "PreTrainedTokenizerFast", |
| "unk_token": "UNK" |
| } |
|
|
