| { |
| "added_tokens_decoder": { |
| "0": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "1": { |
| "content": "<unk>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "65000": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "clean_up_tokenization_spaces": false, |
| "eos_token": "</s>", |
| "extra_special_tokens": {}, |
| "model_max_length": 512, |
| "pad_token": "<pad>", |
| "separate_vocabs": false, |
| "source_lang": "en", |
| "sp_model_kwargs": {}, |
| "target_lang": "fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la", |
| "tokenizer_class": "MarianTokenizer", |
| "unk_token": "<unk>" |
| } |
|
|
