tokenizer_config.json

{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "name_or_path": "models/100mb/tuk_latn_100mb", "model_input_names": ["input_ids", "attention_mask"], "special_tokens_map_file": "models/100mb/tuk_latn_100mb/special_tokens_map.json", "tokenizer_class": "AlbertTokenizer"}