bert-eli5c-retriever / tokenizer_config.json
Jingsong Gao
add tokenizer
0f0d0ff
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "google/bert_uncased_L-8_H-768_A-12", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}