ParaPhraserPlus_1epoch / tokenizer_config.json
sergiyvl's picture
config special_tokens tokenizer_config vocab
b6dcddc
raw
history blame
494 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, "special_tokens_map_file": "/root/.cache/huggingface/transformers/0c7965501fba622370adf334149813060bb231408a6582b155bf623cd1f81d47.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "DeepPavlov/rubert-base-cased-sentence", "do_basic_tokenize": true, "never_split": null}