MLRS
/

mBERTu / tokenizer_config.json
KurtMica's picture
add tokenizer
6a08a78
raw
history blame
429 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, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "name_or_path": "mBERTu", "special_tokens_map_file": "/netscratch/micallef/models/bert_multilingual_mt/special_tokens_map.json", "tokenizer_class": "BertTokenizer"}