| { | |
| "bos_token": "[CLS]", | |
| "cls_token": "[CLS]", | |
| "do_lower_case": true, | |
| "eos_token": "[SEP]", | |
| "mask_token": "[MASK]", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "name_or_path": "/Users/avinashronanki/PycharmProjects/machine_learning/tokenization_pipeline/new_tokenizer", | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": "/Users/avinashronanki/PycharmProjects/machine_learning/tokenization_pipeline/new_tokenizer/special_tokens_map.json", | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]" | |
| } | |