| {"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "C:\\Users\\DiarS/.cache\\huggingface\\transformers\\5fb4590a69eca214db9d31f0a4e90637a90fab773b17d382309a27f2a34da5be.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "../input/mexdpr/LaBSE-BERT/tokenizer", "tokenizer_class": "DPRContextEncoderTokenizer", "vocab_size": 501153} |