russian_toxicity_classifier / tokenizer_config.json
cointegrated's picture
set model_max_length in tokenizer
2b9a086
raw
history blame
585 Bytes
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "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/1f428acdde727eed5de979d6856ce350a470be2a64e134a1fdae04af78a27301.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "DeepPavlov/rubert-base-cased-conversational", "tokenizer_class": "BertTokenizer", "model_max_length": 512}