tokenizer_config.json

{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/content/tokenizer/special_tokens_map.json", "name_or_path": "/content/tokenizer/", "tokenizer_class": "AlbertTokenizer"}