rubert-base-cased-nli-twoway / tokenizer_config.json
cointegrated's picture
Update tokenizer_config.json
bb84213
raw
history blame
545 Bytes
{"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": "/root/.cache/huggingface/transformers/853440ef3f696efb168918bd6c8489323dfaad3a7b308974fa2669336a00d203.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "DeepPavlov/rubert-base-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer", "model_max_length": 512}