tokenizer_config.json

{"do_lower_case": "m.vocab", "remove_space": true, "keep_accents": false, "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": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "/home/josu/nlp/albert_tokenizer/special_tokens_map.json", "name_or_path": "/home/josu/nlp/albert-pt-br", "tokenizer_file": "/home/josu/nlp/albert-pt-br/tokenizer.json", "tokenizer_class": "AlbertTokenizer"}