Czert-B-base-cased-long-zero-shot / tokenizer_config.json
ondfa's picture
initial commit
28bc819
raw
history blame contribute delete
491 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": false, "special_tokens_map_file": "/home/prazak/.cache/huggingface/transformers/0f58b06b684586c2df51e8c72c2bc7363131bc26d6696823fbe13a3a7ea9ac29.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "UWB-AIR/Czert-B-base-cased", "do_basic_tokenize": true, "never_split": null}