| { |
| "added_tokens_decoder": { |
| "524": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "783": { |
| "content": "<unk>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "69666": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "69667": { |
| "content": "ӏ", |
| "lstrip": false, |
| "normalized": true, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "clean_up_tokenization_spaces": false, |
| "eos_token": "</s>", |
| "extra_special_tokens": {}, |
| "model_max_length": 512, |
| "pad_token": "<pad>", |
| "separate_vocabs": false, |
| "source_lang": "mul", |
| "sp_model_kwargs": {}, |
| "target_lang": "mul", |
| "tokenizer_class": "MarianTokenizer", |
| "unk_token": "<unk>" |
| } |
|
|
