grc-por-alignment / tokenizer_config.json
UGARIT's picture
Upload 6 files
986dec9 verified
raw
history blame contribute delete
481 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/content/gdrive/MyDrive/ugaBert/pretrained_mBert_ex3_DFHG/special_tokens_map.json", "name_or_path": "/content/gdrive/MyDrive/ugaBert/pretrained_mBert_ex3_DFHG/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}