rubert-tiny / tokenizer_config.json
cointegrated's picture
The first commit
d0216ba
raw history blame
No virus
347 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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/gd/MyDrive/models/tinybert-ru", "do_basic_tokenize": true, "never_split": null}