| { | |
| "additional_special_tokens": [ | |
| "en_XX", | |
| "ru_RU" | |
| ], | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "mask_token": { | |
| "__type": "AddedToken", | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "model_max_length": 1024, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "sp_model_kwargs": {}, | |
| "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json", | |
| "src_lang": null, | |
| "tgt_lang": null, | |
| "tokenizer_class": "MBart50Tokenizer", | |
| "tokenizer_file": null, | |
| "unk_token": "<unk>" | |
| } | |