| { | |
| "additional_special_tokens": [ | |
| "<s>NOTUSED", | |
| "</s>NOTUSED" | |
| ], | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "mask_token": { | |
| "__type": "AddedToken", | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "max_len": 512, | |
| "model_max_length": 512, | |
| "name_or_path": "./sentencepiece_tokenizers_morphemes_v4/SentencePieceTokenizerMorphemesExcluded_PubMed_Abstracts_CHARS_lowercased_fixed_utf8_V4/", | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "sp_model_kwargs": {}, | |
| "special_tokens_map_file": "./sentencepiece_tokenizers_morphemes_v4/SentencePieceTokenizerMorphemesExcluded_PubMed_Abstracts_CHARS_lowercased_fixed_utf8_V4/special_tokens_map.json", | |
| "tokenizer_class": "CamembertTokenizer", | |
| "unk_token": "<unk>" | |
| } | |